Pasar al contenido principal

COMPROMISE. PRIVACIDAD DE DATOS PARA REDES DE COMUNICACIONES Y BASES DE DATOS DINAMICAS

PID2020-113795RB-C31

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2020
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSITAT POLITECNICA DE CATALUNYA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 42
Encontrada(s) 1 página(s)

UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

On the necessity of counterfeits and deletions for continuous data publishing

  • Tobar Nicolau, Adrián|||0000-0003-0198-2475
  • Parra Arnau, Javier|||0000-0002-1772-1088
  • Forné Muñoz, Jorge|||0000-0002-8401-3292
Continuous data publishing is the scenario where a dataset is published at different times, while it changes between publications through insertion of new tuples, reinsertions, deletions and updates of previously published tuples. Existing algorithms follow a similar structure, requiring in some cases the edition of the dataset in order to feasibly enforce the expected notion of privacy. The possible editions are insertion of synthetic tuples (counterfeits), deletion of part of the dataset, or edition of the sensitive values of a subset of the tuples. In this paper, we study when such operations are unavoidable and prove that the use of centroids as an alternative proposal to data deletion preserves the privacy of the state-of-the-art notions used in the literature., Javier Parra-Arnau is the recipient of a “Ramón y Cajal” fellowship (ref. RYC2021- 034256-I) funded by the Spanish Ministry of Science and Innovation and the European Union – “NextGenerationEU”/PRTR (Plan de Recuperación, Transformación y Resiliencia). This work was also supported by the Spanish Government under the project “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” PID2020-113795RB-C31, funded by MICIU/AEI/10.13039/501100011033; the project “Anonymization technology for AIbased analytics of mo- bility data (MOBILYTICS)” (TED2021-129782B-I00), funded byMICIU/AEI/10.13039/501100011033 and by the European Union NextGenerationEU/PRTR; and funded by the Generalitat de Catalunya, under AGAUR grant “2021 SGR 01413.
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

La publicación de trayectorias: un estudio sobre la protección de la privacidad

  • Guerra Balboa, Patricia
  • Miranda Pascual, Àlex|||0000-0002-1622-993X
  • Parra Arnau, Javier|||0000-0002-1772-1088
  • Forné Muñoz, Jorge|||0000-0002-8401-3292
  • Strufe, Thorsten
El analisis de las trayectorias encierra numerosas ´ promesas, desde mejoras en la gestion del tr ´ afico hasta recomen- ´ daciones de ruta, o incluso en el desarrollo de infraestructuras. Sin embargo, conocer los lugares en los que uno ha estado es extremadamente invasivo. Por ello, surge la necesidad de anonimizar bases de datos de trayectorias, preservando las estadísticas globales utiles para el an ´ alisis, mientras que la ínformacion espec ´ ífica y privada de los individuos permanece inaccesible. En este trabajo analizamos el estado del arte en la publicacion´ de trayectorias con garantías de privacidad, revisando nociones, mecanismos y metricas de utilidad. De este an ´ alisis concluimos ´ limitaciones de las propuestas actuales y teniendo en cuenta tanto los problemas de privacidad como los de utilidad, esbozamos oportunidades de investigacion para el desarrollo de mecanismos éficaces bajo una proteccion espec ´ ífica y rigurosa. Index Terms—privacidad de trayectorias, anonimizacion, no- ´ ciones sintacticas y sem ´ anticas, utilidad, privacidad diferencial., Este trabajo tam- ´ bien ha recibido el apoyo de la Fundaci ´ on “la Caixa” ´ (codigo de beca LCF/BQ/PR20/11770009), del programa ´ H2020 de la Union Europea (acuerdo de subvenci ´ on Marie ´ Skłodowska-Curie n.º 847648), del Gobierno de Espana en el ˜ marco del proyecto “COMPROMISE” (PID2020-113795RBC31/AEI/10.13039/501100011033), y del proyecto BMBF “PROPOLIS” (16KIS1393K). Los autores del KIT cuentan con el apoyo de KASTEL Security Research Labs (Tema 46.23 de la Asociacion Helmholtz) y de la Estrategia de ´ Excelencia de Alemania (EXC 2050/1 ‘CeTI’)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Privacy-centered authentication: a new framework and analysis

  • Robles González, Antonio
  • Arias Cabarcos, Patricia
  • Parra Arnau, Javier|||0000-0002-1772-1088
© 2023 Elsevier. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/, The usage of authentication schemes is increasing in our daily life with the ubiquitous spreading Internet services. The verification of user’s identity is still predominantly password-based, despite of being susceptible to various attacks and openly hated by users. Bonneau et al. presented a framework, based on Usability, Deployability, and Security criteria (UDS), to evaluate authentication schemes and find a replacement for passwords. Although the UDS framework is a mature and comprehensive evaluation framework and has been extended by other authors, it does not analyse privacy aspects in the usage of authentication schemes. In the present work, we extend the UDS framework with a privacy category to allow a more comprehensive evaluation, becoming an UDSP framework. We provide a thorough, rigorous assessment of sample authentication schemes, including analyse novel behavioural biometrics. Our work also discusses implementation aspects regarding the new privacy dimension and sketches the prospect of future authentication schemes., Javier Parra-Arnau is the recipient of a “Ramón y Cajal” fellowship (ref. RYC2021–034256-I) funded by the Spanish Ministry of Science and Innovation and the European Union – “NextGenerationEU”/PRTR (Plan de Recuperación, Transformación y Resiliencia). This work was also supported by the Spanish Government under the project “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” PID2020–113795RB-C31, funded by MCIN/AEI/10.13039/501100011033, and through the project “MOBILYTICS” (TED2021–129782B-I00), funded by MCIN/AEI/10.13039/501100011033 and the European Union “NextGenerationEU”/PRTR., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Privacy protection against user profiling through optimal data generalization

  • Gil Espinasa, César
  • Parra Arnau, Javier|||0000-0002-1772-1088
  • Forné Muñoz, Jorge|||0000-0002-8401-3292
Personalized information systems are information-filtering systems that endeavor to tailor information-exchange functionality to the specific interests of their users. The ability of these systems to profile users based on their search queries at Google, disclosed locations at Twitter or rated movies at Netflix, is on the one hand what enables such intelligent functionality, but on the other, the source of serious privacy concerns. Leveraging on the principle of data minimization, we propose a data-generalization mechanism that aims to protect users’ privacy against non-fully trusted personalized information systems. In our approach, a user may like to disclose personal data to such systems when they feel comfortable. But when they do not, they may wish to replace specific and sensitive data with more general and thus less sensitive data, before sharing this information with the personalized system in question. Generalization therefore may protect user privacy to a certain extent, but clearly at the cost of some information loss. In this work, we model mathematically an optimized version of this mechanism and investigate theoretically some key properties of the privacy-utility trade-off posed by this mechanism. Experimental results on two real-world datasets demonstrate how our approach may contribute to privacy protection and show it can outperform state-of-the-art perturbation techniques like data forgery and suppression by providing higher utility for a same privacy level. On a practical level, the implications of our work are diverse in the field of personalized online services. We emphasize that our mechanism allows each user individually to take charge of their own privacy, without the need to go to third parties or share resources with other users. And on the other hand, it provides privacy designers/engineers with a new data-perturbative mechanism with which to evaluate their systems in the presence of data that is likely to be generalizable according to a certain hierarchy, highlighting spatial generalization, with practical application in popular location based services. Overall, a data-perturbation mechanism for privacy protection against user profiling, which is optimal, deterministic, and local, based on a untrusted model towards third parties., Javier Parra-Arnau is the recipient of a ‘‘Ramón y Cajal’’ fellowship (ref. RYC2021-034256-I) funded by the Spanish Ministry of Science and Innovation and the European Union – ‘‘NextGenerationEU’’/PRTR (Plan de Recuperación, Transformación y Resiliencia). This work was also supported by the Spanish Government under the project ‘‘Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)’’ PID2020-113795RB-C31, funded by MCIN/AEI/10.13039/501100011033, Spain; the project ‘‘Anonymization technology for AI-based analytics of mobility data (MOBILYTICS)’’ (TED2021-129782B-I00), funded by MCIN/AEI/10.13039/50110001 1033 and the European Union ‘‘NextGenerationEU’’/PRTR; and funded by the Generalitat de Catalunya, Spain, under AGAUR grant ‘‘2021 SGR 01413’’., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

m-Eligibility with minimum counterfeits and deletions for privacy protection in continuous data publishing

  • Tobar Nicolau, Adrián|||0000-0003-0198-2475
  • Parra Arnau, Javier|||0000-0002-1772-1088
  • Forné Muñoz, Jorge|||0000-0002-8401-3292
  • Pallarès Segarra, Esteve|||0000-0001-6966-8349
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., Continuous data publishing consists in the republication of updating microdata. The most relevant syntactic notions in continuous data publishing are based on m-invariance. This notion enforces that no user can be distinguished among, at least, m-1 other users, each with distinct secret data. To achieve m-invariance, the existing methods must first alter the dataset to satisfy a property called m-eligibility. Essentially, a dataset can be made m-invariant if and only if it satisfies the m-eligibility constraint. Although guaranteeing the m-eligibility property is a crucial step, no theoretical study of the best strategies to achieve it has been carried out. This paper performs such a study by giving strategies and demonstrating their optimality under two approaches: insertion of counterfeit tuples and partial publication. The empirical evaluation of our proposal shows a significant reduction on the number of modifications needed to enforce m-eligbility of up to 41% with respect to the literature., Javier Parra-Arnau is the recipient of a “Ram´ on y Cajal” fellowship (ref. RYC2021-034256-I) funded by the Spanish Ministry of Science and Innovation and the European Union– “NextGenerationEU”/PRTR (Plan de Recuperaci´ on, Transformaci´ on y Resiliencia). This work was also supported by the Spanish Government under the project “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” PID2020-113795RB-C31, funded by MCIN/AEI/10.13039/501100011033; the project “Anonymization technology for AI-based analytics of mobility data (MOBILYTICS)” (TED2021-129782B-I00), funded by MCIN/AEI/10.13039/501100011033 and the European Union“NextGenerationEU”/PRTR; andfundedbytheGeneralitat de Catalunya, under AGAUR grant “2021 SGR 01413”.
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Generación sintética de trayectorias mediante aprendizaje profundo con garantías de privacidad diferencial

  • Rubio Jornet, Víctor|||0009-0003-5977-2419
  • Parra Arnau, Javier|||0000-0002-1772-1088
  • Forné Muñoz, Jorge|||0000-0002-8401-3292
La generación sintética de trayectorias es cru- cial para poder realizar estudios y análisis en diferentes campos, como la movilidad urbana, los protocolos de redes móviles, la epidemiología computacional o la simulación de cambios en la movilidad para la planificación urbana. Actual- mente, se ha observado que la generación de datos sintéticos sin protección adicional puede poner en riesgo la privacidad de los usuarios, dado que los modelos de aprendizaje profundo actuales son ataques de inferencia de membresía. un modelo de aprendizaje profundo ya existente llamado MoveSim, el cual genera datos sintéticos Este modelo ha sido modificado ferencialmente privado y, de esta manera, garantizar la privacidad de los usuarios que han proporcionado sus datos sin perder un rendimiento sustancial del modelo., Javier Parra-Arnau es el beneficiario de una beca Ramón y Cajal (ref. RYC2021-034256-1) financiada por el Ministerio de Ciencia e Innovación de España y la Unión Europea - "NextGenerationEU”/PRTR (Plan de Recuperación, Transformación y Resiliencia). Este trabajo también ha sido apoyado por el Gobierno español a través del proyecto “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE” PID2020-113795RB-C31, financiado por MCIN/AEI/10.13039/501100011033, y a través del proyecto "MOBILYTICS” (TED2021-129782B-100), financiado por MCIN/AE1/10.13039/501100011033 y la Unión Europea "NextGenerationEU”/PRTR y financiado por la Generalitat de Catalunya mediante la beca AGAUR 72021 SGR 01413”., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

G-3MRP: a game-theoretical multimedia multimetric map-aware routing1 protocol for vehicular ad hoc networks

  • Mohamad Mezher, Ahmad
  • Aguilar Igartua, Mónica|||0000-0002-6518-888X
© 2022 Elsevier. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/, The particular requirements and special features of vehicular ad hoc networks (VANETs) (e.g., special mo8 bility patterns, short link lifetimes, rapid topology changes) involve challenges for the research community. 9 One of these challenges is the development of new routing protocols specially designed for VANETs. In 10 this paper, we present a novel game-theoretical approach of a multimetric geographical routing protocol for 11 VANETs to forward video-reporting messages in smart cities. Game theory is considered a very interesting 12 theoretical framework to analyze and optimize resource allocation problems in digital communication sce13 narios. Our contribution has shown to enhance the overall performance of VANETs in urban scenarios, in 14 terms of percentage of packet losses, average end-to-end packet delay and peak signal to noise ratio (PSNR)., This work was supported by the Spanish Government under research project “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” PID2020-113795RB-C31, funded by MCIN/AEI/10.13039/501100011033. Ahmad M. Mezher holds a McCain Postdoctoral Fellowship in Innovation with the Electrical and Computer Engineering department at the University of New Brunswick (UNB), Canada ., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Ataque de inferencia de membresía a trayectorias, Membership Inference attack to trajectories

  • Rubio Jornet, Víctor|||0009-0003-5977-2419
  • Irurre Martínez, Pol
  • Roca Oliver, Ramon
  • Forné Muñoz, Jorge|||0000-0002-8401-3292
  • Parra Arnau, Javier|||0000-0002-1772-1088
La generación sintética de trayectorias es crucial para realizar estudios y análisis en campos como la movilidad sostenible, protocolos de redes móviles, epidemiología computacional o en la simulación de cambios en la movilidad para la planificación urbana. Desafortunadamente, se ha observado con diferentes tipos de datos que el uso de generadores sintéticos no es suficiente para garantizar la privacidad de los usuarios que ceden su información, ya que estos datos son susceptibles a ataques de inferencia de membresía. Este hecho, aunque se puede asumir trasladable al campo de la movilidad, no ha sido analizado hasta la fecha exclusivamente con trayectorias. En este artículo analizamos la posibilidad de realizar ataques de inferencia de membresía sobre trayectorias sintéticas basándonos en soluciones ya existentes en otros campos. Definimos un ataque de inferencia de membresía para trayectorias y medimos la privacidad empírica de conjuntos de datos sintéticos e-diferencialmente privados. El ataque se ha realizado a un conjunto de trayectorias con y sin privacidad diferencial y se ha analizado la ganancia de privacidad que aporta proteger los datos con este mecanismo., Javier Parra-Arnau es el beneficiario de una beca Ram´on y Cajal (ref. RYC2021-034256-I) financiada por el Ministerio de Ciencia e Innovaci´on de Espa˜na y la Uni´onEuropea- ”NextGenerationEU”/PRTR (Plan deRecuperaci´on, Transformaci´on y Resiliencia). Este trabajo tambi´en ha sido apoyado por el Gobierno espa˜nol a trav´es del proyecto ”Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE” PID2020-113795RB-C31, financiado por MCIN/AEI/10.13039/501100011033, y a trav´es del proyecto”MOBILYTICS” (TED2021-129782B-I00), financiado porMCIN/AEI/10.13039/501100011033ylaUni´onEuropea ”NextGenerationEU”/PRTRyfinanciado por laGeneralitat deCatalunyamediantelabecaAGAUR”2021SGR01413”. V´ıctorRubioJornet cuentaconel apoyodel programapredoctoralAGAUR-FIayudas (2024FI-100762) JoanOr´ode laSecretar´ıadeUniversidades e Investigaci´ondelDepartamentodeInvestigaci´onyUniversidadesde laGeneralitatde CatalunyaydelFondoSocialEuropeoPlus., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

A taxonomy of syntactic privacy notions for continuous data publishing

  • Tobar Nicolau, Adrián|||0000-0003-0198-2475
  • Parra Arnau, Javier|||0000-0002-1772-1088
  • Forné Muñoz, Jorge|||0000-0002-8401-3292
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., Continuous data publishing aims to anonymise the next publication of changing microdata while preserving privacy. The microdata can change between publications via additions, deletions, insertions, and updates. There are numerous proposals for different database types, adversaries, attacks, and notions. However, many anonymization algorithms include notions of privacy and adversarial models that are specific to the context, with their own terminology and notation. Unfortunately, these proposals are difficult to generalize or translate them to other contexts complicating their understanding and comparison. To address these issues, we propose a taxonomy of anonymization technologies, compare existing solutions, and develop a unifying framework that not only harmonizes concepts and terminology but also notation and nomenclature. We analyze the current state of the art and recent advances in the literature. The analysis enables us to understand the significance and appropriateness of the various proposals in achieving privacy., Javier Parra-Arnau is the recipient of a “Ramón y Cajal” fellowship (ref. RYC2021-034256-I) funded y the Spanish Ministry of Science and Innovation and the European Union– “NextGenerationEU”/PRTR (Plan de Recuperación, Transformación y Resiliencia). This work was also supported by the Spanish Government under the project “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” PID2020-113795RB-C31, funded by MCIN/AEI/10.13039/501100011033, and through the project “MOBILYTICS” (TED2021-129782B-I00), funded by MCIN/AEI/10.13039/501100011033 and the European Union “NextGenerationEU”/PRTR.
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Differentially private publication of database streams via hybrid video coding

  • Parra Arnau, Javier|||0000-0002-1772-1088
  • Strufe, Thorsten
  • Domingo Ferrer, Josep
While most anonymization technology available today is designed for static and small data, the current picture is of massive volumes of dynamic data arriving at unprecedented velocities. From the standpoint of anonymization, the most challenging type of dynamic data is data streams. However, while the majority of proposals deal with publishing either count-based or aggregated statistics about the underlying stream, little attention has been paid to the problem of continuously publishing the stream itself with differential privacy guarantees. In this work, we propose an anonymization method that can publish multiple numerical-attribute, finite microdata streams with high protection as well as high utility, the latter aspect measured as data distortion, delay and record reordering. Our method, which relies on the well-known differential pulse-code modulation scheme, adapts techniques originally intended for hybrid video encoding, to favor and leverage dependencies among the blocks of the original stream and thereby reduce data distortion. The proposed solution is assessed experimentally on two of the largest data sets in the scientific community working in data anonymization. Our extensive empirical evaluation shows the trade-off among privacy protection, data distortion, delay and record reordering, and demonstrates the suitability of adapting video-compression techniques to anonymize database streams., J. Parra-Arnau is the recipient of a Juan de la Cierva postdoctoral fellowship, IJCI-2016-28239, from the Spanish Ministry of Economy and Competitiveness, and an Alexander von Humboldt postdoctoral fellow. The project that gave rise to these results received the support of a fellowship from ‘‘la Caixa’’ Foundation (ID 100010434) and from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-curie grant agreement No. 847648. The fellowship code is LCF/BQ/PR20/11770009. This work was also supported by the Spanish Government under research project ‘‘Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)" (PID2020-113795RB-C31/AEI/10.13039/501100011033), and by the German Federal Ministry of Education and Research through the project 16KIS1393K "PROPOLIS".
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

On the adaptation of trajectory generative models to enforce differential privacy through gradient perturbation

  • Rubio Jornet, Víctor|||0009-0003-5977-2419
  • Parra Arnau, Javier|||0000-0002-1772-1088
  • Forné Muñoz, Jorge|||0000-0002-8401-3292
Synthetic trajectories have become a crucial tool for enabling data sharing in domains such as telecommunications and urban planning, yet most generators provide neither formal privacy guarantees nor empirical validation of the protection they claim. This paper investigates whether state-of-the-art deep learning trajectory generators can be adapted to satisfy differential privacy (DP) while retaining usable utility, and makes three contributions. First, we analyze 16 state-of-the-art generators and determine which can be trained with Differentially Private Stochastic Gradient Descent (DP-SGD), showing that common architectural choices — such as index-based coordinate look-ups at inference — silently void the guarantee. Second, we present Sec-LSTM-TrajGAN, a DP adaptation of LSTM-TrajGAN, a well-known trajectory generator chosen after the analysis of the existing models. Third, we introduce RouteMIA, to our knowledge the first closed-box membership inference attack tailored to synthetic trajectories, which adapts the distanceto-closest-record attack to sequential spatio-temporal data and requires access only to the released dataset. Evaluating on GeoLife (17, 000 trajectories) and Porto (100, 000 trajectories) datasets for several scenarios of increasing privacy. RouteMIA attains an AUC of 0.59 and 0.55 against the non-private models, which drops to ˜ 0.50 — chance level — for every private configuration. Notably, gradient clipping alone, with no noise added, already accounts for this entire empirical gain, at a utility cost of a distance JSD rising from 0.12 to 0.20 on Porto and essentially none on GeoLife, whereas strict budgets (e = 3) degrade GeoLife markedly (distance JSD up to 0.35). Per-example clipping, not the noise, therefore delivers the measurable protection against this attack — a cheap empirical complement to, but not a replacement for, formal guarantees., This work was supported in part by Spanish Government, funded by Ministerio de Ciencia e Innovación (MCIN)/Agencia Estatal de Investigación (AEI)/10.13039/501100011033 through the research project ‘‘DIstributed Smart COmmunications with Verifiable EneRgy-optimal Yields (DISCOVERY)’’ under Grant PID2023-148716OB-C32, through the research project ‘‘Privacy-Preserving Techniques for Mobility Data (PRIMOD)’’ under Grant CNS2025-166870, through the research project ‘‘Anonymization Technology for Artificial Intelligence (AI)-Based Analytics of Mobility Data (MOBILYTICS)’’ under Grant TED2021-129782B-I00, and through the research project ‘‘Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)’’ under Grant PID2020-113795RB-C31; in part by the project MOBILYTICS funded by European Union—NextGenerationEU/Recovery, Transformation and Resilience Plan (PRTR); and in part by the Generalitat de Catalunya through AGAUR under Grant 2021 SGR 01413. The work of Víctor Rubio-Jornet was supported by the Joan Oró Agència de Gestió d’Ajuts Universitaris i de Recerca (AGAUR)-Formació d’Investigadors (FI) Predoctoral Program, funded by the Secretariat of Universities and Research of the Department of Research and Universities of the Generalitat of Catalonia and European Social Fund Plus under Grant 2024 FI-1 00762. The work of Javier Parra-Arnau was supported by Ramón y Cajal Grant through Spanish Ministry of Science and Innovation and European Union—‘‘NextGenerationEU’’/PRTR under Grant RYC2021-034256-I., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Strategic deployment of RSUs in urban settings: optimizing IEEE 802.11p infrastructure

  • Astudillo Leon, Juan Pablo
  • Busson, Anthony
  • Cruz Llopis, Luis Javier de la|||0000-0003-4171-8310
  • Begin, Thomas
  • Boukerche, Azzedine
© 2024 Elsevier. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/, The efficient deployment of Roadside Units (RSUs) in an infrastructure based on IEEE 802.11p is essential for delivering Internet-based services to vehicles. In this paper, we introduce novel strategies that, in contrast to prior works, exclusively rely on the average vehicular density within specific urban areas, and these strategies depend on a performance model of IEEE 802.11p for guidance and decision-making regarding RSU placement. This minimal upfront information contributes to the practicality and ease of implementation of our strategies. We apply our strategies to three real-world urban scenarios, utilizing the ns-3 and sumo simulators for validation. This study contributes to three fundamental aspects. First, we establish that any efficient deployment of RSUs is closely linked to the unique characteristics of the city under consideration such as the street layout and spatial density of vehicles. In other words, the characteristics of an efficient RSU deployment are unique to each city. Second, we show that the optimal strategy is not to place the RSUs at the locations with the highest traffic density. Instead, with the help of an analytical performance model of IEEE 802.11, we propose a more efficient strategy wherein the location of each RSU is determined to maximize the number of vehicles receiving the target QoS. This can lead to a significant drop in the number of RSUs required to equip a city. Finally, we demonstrate that, by preventing the use of the lowest transmission rate of IEEE 802.11p at each RSU, a collective benefit can be achieved, even though each RSU experiences a shorter radio range., This work was partially supported by the Spanish Government under research project ”Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” PID2020-113795RB-C31, funded by MICIU/AEI/10.13039/501100011033, research project ”Anonymization technology for AI-based analytics of mobility data (MOBILYTICS)”, TED2021-129782B-I00, funded by MICIU/AEI/10.13039/501100011033 and by the European Union NextGenerationEU/PRTR, and by the Generalitat de Catalunya, under AGAUR grant ”2021 SGR 01413”., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Federated learning for smart charging of connected electric vehicles

  • Al-zuhairi, Yaqoob
  • Kannan, Prashanth
  • Aguilar Igartua, Mónica|||0000-0002-6518-888X
Due to rising concerns over climate change, air pollution and clean energy awareness, the demand for electric vehicles (EVs) and renewable energy generation has increased in recent years. The main objective of this research is to design a decentralized smart charging coordination framework for EVs based on federated learning (FL) algorithms in order to provide an acceptable collaboratively learning model with privacy preservation of EVs, improve charging scenarios, contribute to smart grid stabilization, meet EVs energy requirements wherever and whenever they request, and gain welfare for EV owners. Moreover, FL is introduced with the goal of bringing machine learning (ML) down to the edge level in vehicular networks. Ultimately, a multimetric routing protocol is also used to predict the best route for transmitting messages among EVs, infrastructures, charging stations (CSs), and central servers., This work was supported by the Spanish Government under research project “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” PID2020-113795RBC31/AEI/10.13039/501100011033., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

On the privacy–utility trade-off in differentially private hierarchical text classification

  • Wunderlich, Dominik
  • Bernau, Daniel
  • Aldà, Francesco
  • Parra Arnau, Javier|||0000-0002-1772-1088
  • Strufe, Thorsten
Hierarchical text classification consists of classifying text documents into a hierarchy of classes and sub-classes. Although Artificial Neural Networks have proved useful to perform this task, unfortunately, they can leak training data information to adversaries due to training data memorization. Using differential privacy during model training can mitigate leakage attacks against trained models, enabling the models to be shared safely at the cost of reduced model accuracy. This work investigates the privacy–utility trade-off in hierarchical text classification with differential privacy guarantees, and it identifies neural network architectures that offer superior trade-offs. To this end, we use a white-box membership inference attack to empirically assess the information leakage of three widely used neural network architectures. We show that large differential privacy parameters already suffice to completely mitigate membership inference attacks, thus resulting only in a moderate decrease in model utility. More specifically, for large datasets with long texts, we observed Transformer-based models to achieve an overall favorable privacy–utility trade-off, while for smaller datasets with shorter texts, convolutional neural networks are preferable., This work has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No. 825333 (MOSAICROWN). The project that gave rise to these results received the support of a fellowship from “la Caixa” Foundation (ID 100010434) and from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 847648. The fellowship code is LCF/BQ/PR20/11770009. The work of Javier Parra-Arnau has been supported through an Alexander von Humboldt PostDoctoral Fellowship. This work was also supported by the Spanish Government under research project “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” (PID2020-113795RBC31/AEI/10.13039/501100011033).
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

A reinforcement learning congestion control algorithm for smart grid networks

  • Andrade Zambrano, Argenis Ronaldo
  • Astudillo Leon, Juan Pablo
  • Morocho Cayamcela, Manuel Eugenio
  • Lemus Cárdenas, Leticia
  • Cruz Llopis, Luis Javier de la|||0000-0003-4171-8310
Modern electrical systems are evolving with data communication networks, ushering in upgraded electrical infrastructures and enabling bidirectional communication between utility grids and consumers. The selection of communication technologies is crucial, where wireless communications have emerged as one of the main benefactor technologies due to its cost-effectiveness, scalability, and ease of deployment. Ensuring the streamlined transmission of diverse applications between residential users and utility control centers is crucial for the effective data delivery in smart grids. This paper proposes a congestion control mechanism tailored to smart grid applications using unreliable transport protocols such as UDP, which, unlike TCP, lacks inherent congestion control, presenting a significant challenge to the performance of the network. In this article, we have exploited a reinforcement learning (RL) algorithm and a deep Q-neural network (DQN), to manage congestion control under a UDP environment. In this particular instance, the DQN model learns on its own from interactions with the environment without the need to generate a dataset, rendering it apt for intricate and dynamic scenarios within smart grid communications. Our evaluation covers two scenarios: 1) a grid-like configuration, and 2) urban scenarios considering the deployment of smart meters in the cities of Montreal, Berlin and Beijing. These evaluations provide a comprehensive examination of the proposed DQN-based congestion control approach under different conditions, showing its effectiveness and adaptability. Conducting a comprehensive performance assessment in both scenarios leads to improvements in metrics such as packet delivery ratio, network throughput, fairness between different traffic sources, packet network transit time, and QoS provision., This work was supported in part by the Spanish Government under the Research Project ‘‘Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)’’ under Grant PID2020-113795RB-C31; in part by MICIU/AEI/10.13039/501100011033 under the Research Project ‘‘Anonymization Technology for AI-Based Analytics of Mobility Data (MOBILYTICS)’’ under Grant TED2021-129782B-I00; in part by MICIU/AEI/10.13039/501100011033; in part by European Union NextGenerationEU/PRTR; and in part by the Generalitat de Catalunya through AGAUR under Grant 2021 SGR 01413., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Privacy-aware vehicle emissions control system for traffic light intersections

  • Barbecho Bautista, Pablo
  • Urquiza Aguiar, Luis Felipe
  • Aguilar Igartua, Mónica|||0000-0002-6518-888X
This paper proposes a privacy-aware reinforcement learning (RL) framework to reduce carbon emissions of vehicles approaching light traffic intersections. Taking advantage of vehicular communications, traffic lights disseminate their state (i.e., traffic light cycle) among vehicles in their proximity. Then, the RL model is trained using public traffic lights data while preserving private car information locally (i.e., at the vehicle premises). Vehicles act as the agents of the model, and traffic infrastructure serves as the environment where the agent lives. Each time, the RL model decides if the vehicle should accelerate or decelerate (i.e., the model action) based on received traffic light observations. The optimal RL model strategy, dictating vehicles' driving speed, is learned following the proximal policy optimization algorithm. Results show that by moderating vehicles' speed when approximating traffic light intersections, gas emissions are reduced by 25% CO2 and 38% NOx emissions. The same happens for EVs that reduce energy consumption by 20W/h compared to not using the model. at intersections. The final impact of using the model refers to a negligible increment of 20s in the trip duration., The Spanish Government supported this work under the research project "Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data" (COMPROMISE) (PID2020- 113795RB-C31/AEI/10.13039/501100011033)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

SoK: differentially private publication of trajectory data

  • Miranda Pascual, Àlex|||0000-0002-1622-993X
  • Guerra Balboa, Patricia
  • Parra Arnau, Javier|||0000-0002-1772-1088
  • Forné Muñoz, Jorge|||0000-0002-8401-3292
  • Strufe, Thorsten
Trajectory analysis holds many promises, from improvements in traffic management to routing advice or infrastructure development. However, learning users’ paths is extremely privacy-invasive. Therefore, there is a necessity to protect trajectories such that we preserve the global properties, useful for analysis, while specific and private information of individuals remains inaccessible. Trajectories, however, are difficult to protect, since they are sequential, highly dimensional, correlated, bound to geophysical restrictions, and easily mapped to semantic points of interest. This paper aims to establish a systematic framework on protective masking measures for trajectory databases with differentially private (DP) guarantees, including also utility properties, derived from ideas and limitations of existing proposals. To reach this goal, we systematize the utility metrics used throughout the literature, deeply analyze the DP granularity notions, explore and elaborate on the state of the art on privacy-enhancing mechanisms and their problems, and expose the main limitations of DP notions in the context of trajectories., We would like to thank the reviewers and shepherd for their useful comments and suggestions in the improvement of this paper. Javier Parra-Arnau is the recipient of a “Ramón y Cajal” fellowship funded by the Spanish Ministry of Science and Innovation. This work also received support from “la Caixa” Foundation (fellowship code LCF/BQ/PR20/11770009), the European Union’s H2020 program (Marie Skłodowska-Curie grant agreement № 847648) from the Government of Spain under the project “COMPROMISE” (PID2020-113795RB-C31/AEI/10.13039/501100011033), and from the BMBF project “PROPOLIS” (16KIS1393K). The authors at KIT are supported by KASTEL Security Research Labs (Topic 46.23 of the Helmholtz Association) and Germany’s Excellence Strategy (EXC 2050/1 ‘CeTI’; ID 390696704)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Uncoordinated syntactic privacy: a new composable metric for multiple, independent data publishing

  • Tobar Nicolau, Adrián|||0000-0003-0198-2475
  • Parra Arnau, Javier|||0000-0002-1772-1088
  • Forné Muñoz, Jorge|||0000-0002-8401-3292
  • Torra, Vicenç
A privacy model is a privacy condition, dependent on a parameter, that guarantees an upper bound on the risk of reidentification disclosure and maybe also on the risk of attribute disclosure by an adversary. A privacy model is composable if the privacy guarantees of the model are preserved, possibly to a limited extent, after repeated independent application of the privacy model. From the opposite perspective, a privacy model is not composable if multiple independent data releases, each of them satisfying the requirements of the privacy model, may result in a privacy breach. Current privacy models are broadly classified into syntactic ones (such as k-anonymity and l-diversity) and semantic ones, which essentially refer to e -differential privacy (e-DP) and variations thereof. While e-DP and its variants offer strong composability properties, syntactic notions are not composable unless data releases are conducted by a single, centralized data holder that uses specialized notions such as m-invariance and t -safety. In this work, we propose m-uncoordinated-syntactic-privacy (m-USP), the first syntactic notion with composability properties for the independent publication of nondisjoint data, in other words, without a centralized data holder. Theoretical results are formally proven, and experimental results demonstrate that the risk to individuals does not increase significantly, in contrast to non-composable methods, that are susceptible to attribute disclosure. In most cases, the utility degradation caused by the extra protection is less than 5% and decreases as the value of m increases., Javier Parra-Arnau is the recipient of a “Ram´ on y Cajal” fellowship (ref. RYC2021-034256-I) funded by the Spanish Ministry of Science and Innovation and the European Union– “NextGenerationEU”/PRTR (Plan de Recuperaci´ on, Transformaci´ on y Resiliencia). This work was also supported by the Spanish Government under the following projects: ”DIstributed Smart Communications with Verifiable EneRgy-optimal Yields (DISCOVERY)” PID2023-148716OB-C32, funded by MCIN/AEI/10.13039/501100011033; “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” PID2020-113795RBC31, funded by MICIU/AEI/10.13039/501100011033; and “Anonymization technology for AI-based analytics of mobility data (MOBILYTICS)” (TED2021-129782B-I00), funded by MICIU/AEI/10.13039/501100011033 and by the European Union NextGenerationEU/PRTR. This work was also partially funded by the Generalitat de Catalunya, under AGAUR grant “2021 SGR 01413”; was partially supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation; and received support by the project ”Privacy for complex data” (VR 2022-04645).
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

A machine learning based Distributed Congestion Control Protocol for multi-hop wireless networks

  • Astudillo Leon, Juan Pablo
  • Cruz Llopis, Luis Javier de la|||0000-0003-4171-8310
  • Rico Novella, Francisco José|||0000-0003-1025-5181
The application areas of multi-hop wireless networks are expected to experience sustained growth in the next years. This growth will be further supported by the current possibility of providing low-cost communication capabilities to any device. One of the main issues to consider with this type of networks is congestion control, that is, avoiding an excessive volume of data traffic that could lead to a loss of performance. In this work, a distributed congestion control mechanism is proposed for generic multi-hop networks. Different categories of data traffic are taken into account, each of them with different quality of service requirements. The mechanism is based on machine learning techniques, specifically, the CatBoost algorithm that uses gradient boosting on decision trees. The obtained decision trees are used to predict whether the packets to be transmitted over the network will reach their destination on time or not. This prediction will be made based on the network load state, which will be quantified by means of two parameters: the utilization factor of the different transmission channels, and the occupancy of the buffers of the network nodes. To make the values of these parameters available to all nodes in the network, an appropriate dissemination protocol has also been designed. Besides, a method to assign different transmission priorities to each traffic category, based on the estimation of the network resources required at any time, has also been included. The complete system has been implemented and evaluated through simulations, which show the correct functionality and the improvements obtained in terms of packet delivery ratio, network transit time, and traffic differentiation., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Anàlisi de la campanya de recollida de dades de mobilitat a la comunitat UPC amb l’eina MobilitApp

  • Aguilar Igartua, Mónica|||0000-0002-6518-888X
  • Villarroya Saladié, Albert
  • Gotanegra Estañol, Miquel
  • Caravaca Ibáñez, Gerard
  • de Mingo Esteban, Mireia
La Universitat Politècnica de Catalunya (UPC) <https://www.upc.edu> està compromesa amb la sostenibilitat i la reducció de la petjada de carboni. UPC Sostenible <https://sostenible.upc.edu> estima que el 65% de les emissions que generem com a universitat són degudes als desplaçaments diaris de l’estudiantat, PTGAS (personal tècnic, de gestió i d'administració i serveis) i PDI (personal docent i investigador) per arribar als campus. Per incentivar l’ús de modes de transport sostenibles i millorar la mobilitat per accedir als campus, és imprescindible disposar de dades de qualitat., Peer Reviewed, Objectius de Desenvolupament Sostenible::11 - Ciutats i Comunitats Sostenibles, Objectius de Desenvolupament Sostenible::11 - Ciutats i Comunitats Sostenibles::11.2 - Per a 2030, proporcionar accés a sistemes de transport segurs, assequibles, accessi­bles i sostenibles per a totes les persones, i millorar la seguretat viària, en particular mitjan­çant l’ampliació del transport públic, amb especial atenció a les necessitats de les persones en situació vulnerable, dones, nenes, nens, persones amb discapacitat i persones grans, Objectius de Desenvolupament Sostenible::11 - Ciutats i Comunitats Sostenibles::11.3 - Per a 2030, augmentar la urbanització inclusiva i sostenible, així com la capacitat de planificar i gestionar de manera participativa, integrada i sostenible els assentaments humans a tots els països
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

a,m-warden: a syntactic privacy notion for continuous data publishing against probabilistic attacks

  • Tobar Nicolau, Adrián|||0000-0003-0198-2475
  • Parra Arnau, Javier|||0000-0002-1772-1088
  • Forné Muñoz, Jorge|||0000-0002-8401-3292
Publishing private information can be very useful for multiple data mining processes, but prior anonymization is necessary to protect the privacy of the individuals on whom data are collected. This is especially sensitive in dynamic publishing scenarios where multiple releases with common information are published over time; and even more so against probabilistic attackers, i.e., those with statistical knowledge of the dataset. In this paper, we focus on the specific scenario of continuous data publishing, where existing privacy notions cannot offer protection against those attackers in dynamic settings (i.e., where record additions and deletions are considered). To tackle this limitation, we propose a,mwarden, a new syntactic privacy notion that can provide an explicit upper bound on disclosure risk against such attacks under the Smart Random World Assumption. We demonstrate the theoretical guarantees of this notion, prove the complexity of an optimal implementation, propose a proof-of-concept implementation of an algorithm that can enforce it, and perform an experimental evaluation to support our claims. Our experimental results show that a,m-warden can reduce the performance and certainty of probabilistic attacks by more than 10% with respect to tsafety., The project that gave rise to these results was supported by the Spanish Government under research project “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” (PID2020-113795RBC31/AEI/10.13039/501100011033). This work was also supported by a fellowship from “la Caixa” Foundation (ID 100010434) and from the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 847648. The fellowship code is LCF/BQ/PR20/11770009., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Anàlisi de la campanya de recollida de dades de mobilitat a la comunitat UPC amb l’eina MobilitApp

  • Aguilar Igartua, Mónica
  • Villarroya Saladié, Albert
  • Gotanegra Estañol, Miquel
  • Caravaca Ibáñez, Gerard
  • de Mingo Esteban, Mireia
La Universitat Politècnica de Catalunya (UPC) <https://www.upc.edu> està compromesa amb la sostenibilitat i la reducció de la petjada de carboni. UPC Sostenible <https://sostenible.upc.edu> estima que el 65% de les emissions que generem com a universitat són degudes als desplaçaments diaris de l’estudiantat, PTGAS (personal tècnic, de gestió i d'administració i serveis) i PDI (personal docent i investigador) per arribar als campus. Per incentivar l’ús de modes de transport sostenibles i millorar la mobilitat per accedir als campus, és imprescindible disposar de dades de qualitat., Peer Reviewed, Objectius de Desenvolupament Sostenible::11 - Ciutats i Comunitats Sostenibles, Objectius de Desenvolupament Sostenible::11 - Ciutats i Comunitats Sostenibles::11.2 - Per a 2030, proporcionar accés a sistemes de transport segurs, assequibles, accessi­bles i sostenibles per a totes les persones, i millorar la seguretat viària, en particular mitjan­çant l’ampliació del transport públic, amb especial atenció a les necessitats de les persones en situació vulnerable, dones, nenes, nens, persones amb discapacitat i persones grans, Objectius de Desenvolupament Sostenible::11 - Ciutats i Comunitats Sostenibles::11.3 - Per a 2030, augmentar la urbanització inclusiva i sostenible, així com la capacitat de planificar i gestionar de manera participativa, integrada i sostenible els assentaments humans a tots els països, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Privacy-aware vehicle emissions control system for traffic light intersections

  • Barbecho Bautista, Pablo
  • Urquiza Aguiar, Luis Felipe
  • Aguilar Igartua, Mónica
This paper proposes a privacy-aware reinforcement learning (RL) framework to reduce carbon emissions of vehicles approaching light traffic intersections. Taking advantage of vehicular communications, traffic lights disseminate their state (i.e., traffic light cycle) among vehicles in their proximity. Then, the RL model is trained using public traffic lights data while preserving private car information locally (i.e., at the vehicle premises). Vehicles act as the agents of the model, and traffic infrastructure serves as the environment where the agent lives. Each time, the RL model decides if the vehicle should accelerate or decelerate (i.e., the model action) based on received traffic light observations. The optimal RL model strategy, dictating vehicles' driving speed, is learned following the proximal policy optimization algorithm. Results show that by moderating vehicles' speed when approximating traffic light intersections, gas emissions are reduced by 25% CO2 and 38% NOx emissions. The same happens for EVs that reduce energy consumption by 20W/h compared to not using the model. at intersections. The final impact of using the model refers to a negligible increment of 20s in the trip duration., The Spanish Government supported this work under the research project "Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data" (COMPROMISE) (PID2020- 113795RB-C31/AEI/10.13039/501100011033)., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Federated learning for smart charging of connected electric vehicles

  • Al-zuhairi, Yaqoob
  • Kannan, Prashanth
  • Aguilar Igartua, Mónica
Due to rising concerns over climate change, air pollution and clean energy awareness, the demand for electric vehicles (EVs) and renewable energy generation has increased in recent years. The main objective of this research is to design a decentralized smart charging coordination framework for EVs based on federated learning (FL) algorithms in order to provide an acceptable collaboratively learning model with privacy preservation of EVs, improve charging scenarios, contribute to smart grid stabilization, meet EVs energy requirements wherever and whenever they request, and gain welfare for EV owners. Moreover, FL is introduced with the goal of bringing machine learning (ML) down to the edge level in vehicular networks. Ultimately, a multimetric routing protocol is also used to predict the best route for transmitting messages among EVs, infrastructures, charging stations (CSs), and central servers., This work was supported by the Spanish Government under research project “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” PID2020-113795RBC31/AEI/10.13039/501100011033., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

On the necessity of counterfeits and deletions for continuous data publishing

  • Tobar Nicolau, Adrián
  • Parra Arnau, Javier
  • Forné Muñoz, Jorge
Continuous data publishing is the scenario where a dataset is published at different times, while it changes between publications through insertion of new tuples, reinsertions, deletions and updates of previously published tuples. Existing algorithms follow a similar structure, requiring in some cases the edition of the dataset in order to feasibly enforce the expected notion of privacy. The possible editions are insertion of synthetic tuples (counterfeits), deletion of part of the dataset, or edition of the sensitive values of a subset of the tuples. In this paper, we study when such operations are unavoidable and prove that the use of centroids as an alternative proposal to data deletion preserves the privacy of the state-of-the-art notions used in the literature., Javier Parra-Arnau is the recipient of a “Ramón y Cajal” fellowship (ref. RYC2021- 034256-I) funded by the Spanish Ministry of Science and Innovation and the European Union – “NextGenerationEU”/PRTR (Plan de Recuperación, Transformación y Resiliencia). This work was also supported by the Spanish Government under the project “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” PID2020-113795RB-C31, funded by MICIU/AEI/10.13039/501100011033; the project “Anonymization technology for AIbased analytics of mo- bility data (MOBILYTICS)” (TED2021-129782B-I00), funded byMICIU/AEI/10.13039/501100011033 and by the European Union NextGenerationEU/PRTR; and funded by the Generalitat de Catalunya, under AGAUR grant “2021 SGR 01413., Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

A machine learning based Distributed Congestion Control Protocol for multi-hop wireless networks

  • Astudillo Leon, Juan Pablo
  • Cruz Llopis, Luis Javier de la
  • Rico Novella, Francisco José
The application areas of multi-hop wireless networks are expected to experience sustained growth in the next years. This growth will be further supported by the current possibility of providing low-cost communication capabilities to any device. One of the main issues to consider with this type of networks is congestion control, that is, avoiding an excessive volume of data traffic that could lead to a loss of performance. In this work, a distributed congestion control mechanism is proposed for generic multi-hop networks. Different categories of data traffic are taken into account, each of them with different quality of service requirements. The mechanism is based on machine learning techniques, specifically, the CatBoost algorithm that uses gradient boosting on decision trees. The obtained decision trees are used to predict whether the packets to be transmitted over the network will reach their destination on time or not. This prediction will be made based on the network load state, which will be quantified by means of two parameters: the utilization factor of the different transmission channels, and the occupancy of the buffers of the network nodes. To make the values of these parameters available to all nodes in the network, an appropriate dissemination protocol has also been designed. Besides, a method to assign different transmission priorities to each traffic category, based on the estimation of the network resources required at any time, has also been included. The complete system has been implemented and evaluated through simulations, which show the correct functionality and the improvements obtained in terms of packet delivery ratio, network transit time, and traffic differentiation., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Strategic deployment of RSUs in urban settings: optimizing IEEE 802.11p infrastructure

  • Astudillo Leon, Juan Pablo
  • Busson, Anthony
  • Cruz Llopis, Luis Javier de la
  • Begin, Thomas
  • Boukerche, Azzedine
© 2024 Elsevier. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/, The efficient deployment of Roadside Units (RSUs) in an infrastructure based on IEEE 802.11p is essential for delivering Internet-based services to vehicles. In this paper, we introduce novel strategies that, in contrast to prior works, exclusively rely on the average vehicular density within specific urban areas, and these strategies depend on a performance model of IEEE 802.11p for guidance and decision-making regarding RSU placement. This minimal upfront information contributes to the practicality and ease of implementation of our strategies. We apply our strategies to three real-world urban scenarios, utilizing the ns-3 and sumo simulators for validation. This study contributes to three fundamental aspects. First, we establish that any efficient deployment of RSUs is closely linked to the unique characteristics of the city under consideration such as the street layout and spatial density of vehicles. In other words, the characteristics of an efficient RSU deployment are unique to each city. Second, we show that the optimal strategy is not to place the RSUs at the locations with the highest traffic density. Instead, with the help of an analytical performance model of IEEE 802.11, we propose a more efficient strategy wherein the location of each RSU is determined to maximize the number of vehicles receiving the target QoS. This can lead to a significant drop in the number of RSUs required to equip a city. Finally, we demonstrate that, by preventing the use of the lowest transmission rate of IEEE 802.11p at each RSU, a collective benefit can be achieved, even though each RSU experiences a shorter radio range., This work was partially supported by the Spanish Government under research project ”Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” PID2020-113795RB-C31, funded by MICIU/AEI/10.13039/501100011033, research project ”Anonymization technology for AI-based analytics of mobility data (MOBILYTICS)”, TED2021-129782B-I00, funded by MICIU/AEI/10.13039/501100011033 and by the European Union NextGenerationEU/PRTR, and by the Generalitat de Catalunya, under AGAUR grant ”2021 SGR 01413”., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Ataque de inferencia de membresía a trayectorias, Membership Inference attack to trajectories

  • Rubio Jornet, Víctor
  • Irurre Martínez, Pol
  • Roca Oliver, Ramon
  • Forné Muñoz, Jorge
  • Parra Arnau, Javier
La generación sintética de trayectorias es crucial para realizar estudios y análisis en campos como la movilidad sostenible, protocolos de redes móviles, epidemiología computacional o en la simulación de cambios en la movilidad para la planificación urbana. Desafortunadamente, se ha observado con diferentes tipos de datos que el uso de generadores sintéticos no es suficiente para garantizar la privacidad de los usuarios que ceden su información, ya que estos datos son susceptibles a ataques de inferencia de membresía. Este hecho, aunque se puede asumir trasladable al campo de la movilidad, no ha sido analizado hasta la fecha exclusivamente con trayectorias. En este artículo analizamos la posibilidad de realizar ataques de inferencia de membresía sobre trayectorias sintéticas basándonos en soluciones ya existentes en otros campos. Definimos un ataque de inferencia de membresía para trayectorias y medimos la privacidad empírica de conjuntos de datos sintéticos e-diferencialmente privados. El ataque se ha realizado a un conjunto de trayectorias con y sin privacidad diferencial y se ha analizado la ganancia de privacidad que aporta proteger los datos con este mecanismo., Javier Parra-Arnau es el beneficiario de una beca Ram´on y Cajal (ref. RYC2021-034256-I) financiada por el Ministerio de Ciencia e Innovaci´on de Espa˜na y la Uni´onEuropea- ”NextGenerationEU”/PRTR (Plan deRecuperaci´on, Transformaci´on y Resiliencia). Este trabajo tambi´en ha sido apoyado por el Gobierno espa˜nol a trav´es del proyecto ”Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE” PID2020-113795RB-C31, financiado por MCIN/AEI/10.13039/501100011033, y a trav´es del proyecto”MOBILYTICS” (TED2021-129782B-I00), financiado porMCIN/AEI/10.13039/501100011033ylaUni´onEuropea ”NextGenerationEU”/PRTRyfinanciado por laGeneralitat deCatalunyamediantelabecaAGAUR”2021SGR01413”. V´ıctorRubioJornet cuentaconel apoyodel programapredoctoralAGAUR-FIayudas (2024FI-100762) JoanOr´ode laSecretar´ıadeUniversidades e Investigaci´ondelDepartamentodeInvestigaci´onyUniversidadesde laGeneralitatde CatalunyaydelFondoSocialEuropeoPlus., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Privacy protection against user profiling through optimal data generalization

  • Gil Espinasa, César
  • Parra Arnau, Javier
  • Forné Muñoz, Jorge
Personalized information systems are information-filtering systems that endeavor to tailor information-exchange functionality to the specific interests of their users. The ability of these systems to profile users based on their search queries at Google, disclosed locations at Twitter or rated movies at Netflix, is on the one hand what enables such intelligent functionality, but on the other, the source of serious privacy concerns. Leveraging on the principle of data minimization, we propose a data-generalization mechanism that aims to protect users’ privacy against non-fully trusted personalized information systems. In our approach, a user may like to disclose personal data to such systems when they feel comfortable. But when they do not, they may wish to replace specific and sensitive data with more general and thus less sensitive data, before sharing this information with the personalized system in question. Generalization therefore may protect user privacy to a certain extent, but clearly at the cost of some information loss. In this work, we model mathematically an optimized version of this mechanism and investigate theoretically some key properties of the privacy-utility trade-off posed by this mechanism. Experimental results on two real-world datasets demonstrate how our approach may contribute to privacy protection and show it can outperform state-of-the-art perturbation techniques like data forgery and suppression by providing higher utility for a same privacy level. On a practical level, the implications of our work are diverse in the field of personalized online services. We emphasize that our mechanism allows each user individually to take charge of their own privacy, without the need to go to third parties or share resources with other users. And on the other hand, it provides privacy designers/engineers with a new data-perturbative mechanism with which to evaluate their systems in the presence of data that is likely to be generalizable according to a certain hierarchy, highlighting spatial generalization, with practical application in popular location based services. Overall, a data-perturbation mechanism for privacy protection against user profiling, which is optimal, deterministic, and local, based on a untrusted model towards third parties., Javier Parra-Arnau is the recipient of a ‘‘Ramón y Cajal’’ fellowship (ref. RYC2021-034256-I) funded by the Spanish Ministry of Science and Innovation and the European Union – ‘‘NextGenerationEU’’/PRTR (Plan de Recuperación, Transformación y Resiliencia). This work was also supported by the Spanish Government under the project ‘‘Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)’’ PID2020-113795RB-C31, funded by MCIN/AEI/10.13039/501100011033, Spain; the project ‘‘Anonymization technology for AI-based analytics of mobility data (MOBILYTICS)’’ (TED2021-129782B-I00), funded by MCIN/AEI/10.13039/50110001 1033 and the European Union ‘‘NextGenerationEU’’/PRTR; and funded by the Generalitat de Catalunya, Spain, under AGAUR grant ‘‘2021 SGR 01413’’., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

La publicación de trayectorias: un estudio sobre la protección de la privacidad

  • Guerra Balboa, Patricia
  • Miranda Pascual, Àlex
  • Parra Arnau, Javier
  • Forné Muñoz, Jorge
  • Strufe, Thorsten
El analisis de las trayectorias encierra numerosas ´ promesas, desde mejoras en la gestion del tr ´ afico hasta recomen- ´ daciones de ruta, o incluso en el desarrollo de infraestructuras. Sin embargo, conocer los lugares en los que uno ha estado es extremadamente invasivo. Por ello, surge la necesidad de anonimizar bases de datos de trayectorias, preservando las estadísticas globales utiles para el an ´ alisis, mientras que la ínformacion espec ´ ífica y privada de los individuos permanece inaccesible. En este trabajo analizamos el estado del arte en la publicacion´ de trayectorias con garantías de privacidad, revisando nociones, mecanismos y metricas de utilidad. De este an ´ alisis concluimos ´ limitaciones de las propuestas actuales y teniendo en cuenta tanto los problemas de privacidad como los de utilidad, esbozamos oportunidades de investigacion para el desarrollo de mecanismos éficaces bajo una proteccion espec ´ ífica y rigurosa. Index Terms—privacidad de trayectorias, anonimizacion, no- ´ ciones sintacticas y sem ´ anticas, utilidad, privacidad diferencial., Este trabajo tam- ´ bien ha recibido el apoyo de la Fundaci ´ on “la Caixa” ´ (codigo de beca LCF/BQ/PR20/11770009), del programa ´ H2020 de la Union Europea (acuerdo de subvenci ´ on Marie ´ Skłodowska-Curie n.º 847648), del Gobierno de Espana en el ˜ marco del proyecto “COMPROMISE” (PID2020-113795RBC31/AEI/10.13039/501100011033), y del proyecto BMBF “PROPOLIS” (16KIS1393K). Los autores del KIT cuentan con el apoyo de KASTEL Security Research Labs (Tema 46.23 de la Asociacion Helmholtz) y de la Estrategia de ´ Excelencia de Alemania (EXC 2050/1 ‘CeTI’)., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

m-Eligibility with minimum counterfeits and deletions for privacy protection in continuous data publishing

  • Tobar Nicolau, Adrián
  • Parra Arnau, Javier
  • Forné Muñoz, Jorge
  • Pallarès Segarra, Esteve
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., Continuous data publishing consists in the republication of updating microdata. The most relevant syntactic notions in continuous data publishing are based on m-invariance. This notion enforces that no user can be distinguished among, at least, m-1 other users, each with distinct secret data. To achieve m-invariance, the existing methods must first alter the dataset to satisfy a property called m-eligibility. Essentially, a dataset can be made m-invariant if and only if it satisfies the m-eligibility constraint. Although guaranteeing the m-eligibility property is a crucial step, no theoretical study of the best strategies to achieve it has been carried out. This paper performs such a study by giving strategies and demonstrating their optimality under two approaches: insertion of counterfeit tuples and partial publication. The empirical evaluation of our proposal shows a significant reduction on the number of modifications needed to enforce m-eligbility of up to 41% with respect to the literature., Javier Parra-Arnau is the recipient of a “Ram´ on y Cajal” fellowship (ref. RYC2021-034256-I) funded by the Spanish Ministry of Science and Innovation and the European Union– “NextGenerationEU”/PRTR (Plan de Recuperaci´ on, Transformaci´ on y Resiliencia). This work was also supported by the Spanish Government under the project “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” PID2020-113795RB-C31, funded by MCIN/AEI/10.13039/501100011033; the project “Anonymization technology for AI-based analytics of mobility data (MOBILYTICS)” (TED2021-129782B-I00), funded by MCIN/AEI/10.13039/501100011033 and the European Union“NextGenerationEU”/PRTR; andfundedbytheGeneralitat de Catalunya, under AGAUR grant “2021 SGR 01413”., Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

SoK: differentially private publication of trajectory data

  • Miranda Pascual, Àlex
  • Guerra Balboa, Patricia
  • Parra Arnau, Javier
  • Forné Muñoz, Jorge
  • Strufe, Thorsten
Trajectory analysis holds many promises, from improvements in traffic management to routing advice or infrastructure development. However, learning users’ paths is extremely privacy-invasive. Therefore, there is a necessity to protect trajectories such that we preserve the global properties, useful for analysis, while specific and private information of individuals remains inaccessible. Trajectories, however, are difficult to protect, since they are sequential, highly dimensional, correlated, bound to geophysical restrictions, and easily mapped to semantic points of interest. This paper aims to establish a systematic framework on protective masking measures for trajectory databases with differentially private (DP) guarantees, including also utility properties, derived from ideas and limitations of existing proposals. To reach this goal, we systematize the utility metrics used throughout the literature, deeply analyze the DP granularity notions, explore and elaborate on the state of the art on privacy-enhancing mechanisms and their problems, and expose the main limitations of DP notions in the context of trajectories., We would like to thank the reviewers and shepherd for their useful comments and suggestions in the improvement of this paper. Javier Parra-Arnau is the recipient of a “Ramón y Cajal” fellowship funded by the Spanish Ministry of Science and Innovation. This work also received support from “la Caixa” Foundation (fellowship code LCF/BQ/PR20/11770009), the European Union’s H2020 program (Marie Skłodowska-Curie grant agreement № 847648) from the Government of Spain under the project “COMPROMISE” (PID2020-113795RB-C31/AEI/10.13039/501100011033), and from the BMBF project “PROPOLIS” (16KIS1393K). The authors at KIT are supported by KASTEL Security Research Labs (Topic 46.23 of the Helmholtz Association) and Germany’s Excellence Strategy (EXC 2050/1 ‘CeTI’; ID 390696704)., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

On the privacy–utility trade-off in differentially private hierarchical text classification

  • Wunderlich, Dominik
  • Bernau, Daniel
  • Aldà, Francesco
  • Parra Arnau, Javier
  • Strufe, Thorsten
Hierarchical text classification consists of classifying text documents into a hierarchy of classes and sub-classes. Although Artificial Neural Networks have proved useful to perform this task, unfortunately, they can leak training data information to adversaries due to training data memorization. Using differential privacy during model training can mitigate leakage attacks against trained models, enabling the models to be shared safely at the cost of reduced model accuracy. This work investigates the privacy–utility trade-off in hierarchical text classification with differential privacy guarantees, and it identifies neural network architectures that offer superior trade-offs. To this end, we use a white-box membership inference attack to empirically assess the information leakage of three widely used neural network architectures. We show that large differential privacy parameters already suffice to completely mitigate membership inference attacks, thus resulting only in a moderate decrease in model utility. More specifically, for large datasets with long texts, we observed Transformer-based models to achieve an overall favorable privacy–utility trade-off, while for smaller datasets with shorter texts, convolutional neural networks are preferable., This work has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No. 825333 (MOSAICROWN). The project that gave rise to these results received the support of a fellowship from “la Caixa” Foundation (ID 100010434) and from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 847648. The fellowship code is LCF/BQ/PR20/11770009. The work of Javier Parra-Arnau has been supported through an Alexander von Humboldt PostDoctoral Fellowship. This work was also supported by the Spanish Government under research project “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” (PID2020-113795RBC31/AEI/10.13039/501100011033)., Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

A reinforcement learning congestion control algorithm for smart grid networks

  • Andrade Zambrano, Argenis Ronaldo
  • Astudillo Leon, Juan Pablo
  • Morocho Cayamcela, Manuel Eugenio
  • Lemus Cárdenas, Leticia
  • Cruz Llopis, Luis Javier de la
Modern electrical systems are evolving with data communication networks, ushering in upgraded electrical infrastructures and enabling bidirectional communication between utility grids and consumers. The selection of communication technologies is crucial, where wireless communications have emerged as one of the main benefactor technologies due to its cost-effectiveness, scalability, and ease of deployment. Ensuring the streamlined transmission of diverse applications between residential users and utility control centers is crucial for the effective data delivery in smart grids. This paper proposes a congestion control mechanism tailored to smart grid applications using unreliable transport protocols such as UDP, which, unlike TCP, lacks inherent congestion control, presenting a significant challenge to the performance of the network. In this article, we have exploited a reinforcement learning (RL) algorithm and a deep Q-neural network (DQN), to manage congestion control under a UDP environment. In this particular instance, the DQN model learns on its own from interactions with the environment without the need to generate a dataset, rendering it apt for intricate and dynamic scenarios within smart grid communications. Our evaluation covers two scenarios: 1) a grid-like configuration, and 2) urban scenarios considering the deployment of smart meters in the cities of Montreal, Berlin and Beijing. These evaluations provide a comprehensive examination of the proposed DQN-based congestion control approach under different conditions, showing its effectiveness and adaptability. Conducting a comprehensive performance assessment in both scenarios leads to improvements in metrics such as packet delivery ratio, network throughput, fairness between different traffic sources, packet network transit time, and QoS provision., This work was supported in part by the Spanish Government under the Research Project ‘‘Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)’’ under Grant PID2020-113795RB-C31; in part by MICIU/AEI/10.13039/501100011033 under the Research Project ‘‘Anonymization Technology for AI-Based Analytics of Mobility Data (MOBILYTICS)’’ under Grant TED2021-129782B-I00; in part by MICIU/AEI/10.13039/501100011033; in part by European Union NextGenerationEU/PRTR; and in part by the Generalitat de Catalunya through AGAUR under Grant 2021 SGR 01413., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

a,m-warden: a syntactic privacy notion for continuous data publishing against probabilistic attacks

  • Tobar Nicolau, Adrián
  • Parra Arnau, Javier
  • Forné Muñoz, Jorge
Publishing private information can be very useful for multiple data mining processes, but prior anonymization is necessary to protect the privacy of the individuals on whom data are collected. This is especially sensitive in dynamic publishing scenarios where multiple releases with common information are published over time; and even more so against probabilistic attackers, i.e., those with statistical knowledge of the dataset. In this paper, we focus on the specific scenario of continuous data publishing, where existing privacy notions cannot offer protection against those attackers in dynamic settings (i.e., where record additions and deletions are considered). To tackle this limitation, we propose a,mwarden, a new syntactic privacy notion that can provide an explicit upper bound on disclosure risk against such attacks under the Smart Random World Assumption. We demonstrate the theoretical guarantees of this notion, prove the complexity of an optimal implementation, propose a proof-of-concept implementation of an algorithm that can enforce it, and perform an experimental evaluation to support our claims. Our experimental results show that a,m-warden can reduce the performance and certainty of probabilistic attacks by more than 10% with respect to tsafety., The project that gave rise to these results was supported by the Spanish Government under research project “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” (PID2020-113795RBC31/AEI/10.13039/501100011033). This work was also supported by a fellowship from “la Caixa” Foundation (ID 100010434) and from the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 847648. The fellowship code is LCF/BQ/PR20/11770009., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

On the adaptation of trajectory generative models to enforce differential privacy through gradient perturbation

  • Rubio Jornet, Víctor
  • Parra Arnau, Javier
  • Forné Muñoz, Jorge
Synthetic trajectories have become a crucial tool for enabling data sharing in domains such as telecommunications and urban planning, yet most generators provide neither formal privacy guarantees nor empirical validation of the protection they claim. This paper investigates whether state-of-the-art deep learning trajectory generators can be adapted to satisfy differential privacy (DP) while retaining usable utility, and makes three contributions. First, we analyze 16 state-of-the-art generators and determine which can be trained with Differentially Private Stochastic Gradient Descent (DP-SGD), showing that common architectural choices — such as index-based coordinate look-ups at inference — silently void the guarantee. Second, we present Sec-LSTM-TrajGAN, a DP adaptation of LSTM-TrajGAN, a well-known trajectory generator chosen after the analysis of the existing models. Third, we introduce RouteMIA, to our knowledge the first closed-box membership inference attack tailored to synthetic trajectories, which adapts the distanceto-closest-record attack to sequential spatio-temporal data and requires access only to the released dataset. Evaluating on GeoLife (17, 000 trajectories) and Porto (100, 000 trajectories) datasets for several scenarios of increasing privacy. RouteMIA attains an AUC of 0.59 and 0.55 against the non-private models, which drops to ˜ 0.50 — chance level — for every private configuration. Notably, gradient clipping alone, with no noise added, already accounts for this entire empirical gain, at a utility cost of a distance JSD rising from 0.12 to 0.20 on Porto and essentially none on GeoLife, whereas strict budgets (e = 3) degrade GeoLife markedly (distance JSD up to 0.35). Per-example clipping, not the noise, therefore delivers the measurable protection against this attack — a cheap empirical complement to, but not a replacement for, formal guarantees., This work was supported in part by Spanish Government, funded by Ministerio de Ciencia e Innovación (MCIN)/Agencia Estatal de Investigación (AEI)/10.13039/501100011033 through the research project ‘‘DIstributed Smart COmmunications with Verifiable EneRgy-optimal Yields (DISCOVERY)’’ under Grant PID2023-148716OB-C32, through the research project ‘‘Privacy-Preserving Techniques for Mobility Data (PRIMOD)’’ under Grant CNS2025-166870, through the research project ‘‘Anonymization Technology for Artificial Intelligence (AI)-Based Analytics of Mobility Data (MOBILYTICS)’’ under Grant TED2021-129782B-I00, and through the research project ‘‘Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)’’ under Grant PID2020-113795RB-C31; in part by the project MOBILYTICS funded by European Union—NextGenerationEU/Recovery, Transformation and Resilience Plan (PRTR); and in part by the Generalitat de Catalunya through AGAUR under Grant 2021 SGR 01413. The work of Víctor Rubio-Jornet was supported by the Joan Oró Agència de Gestió d’Ajuts Universitaris i de Recerca (AGAUR)-Formació d’Investigadors (FI) Predoctoral Program, funded by the Secretariat of Universities and Research of the Department of Research and Universities of the Generalitat of Catalonia and European Social Fund Plus under Grant 2024 FI-1 00762. The work of Javier Parra-Arnau was supported by Ramón y Cajal Grant through Spanish Ministry of Science and Innovation and European Union—‘‘NextGenerationEU’’/PRTR under Grant RYC2021-034256-I., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Differentially private publication of database streams via hybrid video coding

  • Parra Arnau, Javier
  • Strufe, Thorsten
  • Domingo Ferrer, Josep
While most anonymization technology available today is designed for static and small data, the current picture is of massive volumes of dynamic data arriving at unprecedented velocities. From the standpoint of anonymization, the most challenging type of dynamic data is data streams. However, while the majority of proposals deal with publishing either count-based or aggregated statistics about the underlying stream, little attention has been paid to the problem of continuously publishing the stream itself with differential privacy guarantees. In this work, we propose an anonymization method that can publish multiple numerical-attribute, finite microdata streams with high protection as well as high utility, the latter aspect measured as data distortion, delay and record reordering. Our method, which relies on the well-known differential pulse-code modulation scheme, adapts techniques originally intended for hybrid video encoding, to favor and leverage dependencies among the blocks of the original stream and thereby reduce data distortion. The proposed solution is assessed experimentally on two of the largest data sets in the scientific community working in data anonymization. Our extensive empirical evaluation shows the trade-off among privacy protection, data distortion, delay and record reordering, and demonstrates the suitability of adapting video-compression techniques to anonymize database streams., J. Parra-Arnau is the recipient of a Juan de la Cierva postdoctoral fellowship, IJCI-2016-28239, from the Spanish Ministry of Economy and Competitiveness, and an Alexander von Humboldt postdoctoral fellow. The project that gave rise to these results received the support of a fellowship from ‘‘la Caixa’’ Foundation (ID 100010434) and from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-curie grant agreement No. 847648. The fellowship code is LCF/BQ/PR20/11770009. This work was also supported by the Spanish Government under research project ‘‘Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)" (PID2020-113795RB-C31/AEI/10.13039/501100011033), and by the German Federal Ministry of Education and Research through the project 16KIS1393K "PROPOLIS"., Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

A taxonomy of syntactic privacy notions for continuous data publishing

  • Tobar Nicolau, Adrián
  • Parra Arnau, Javier
  • Forné Muñoz, Jorge
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., Continuous data publishing aims to anonymise the next publication of changing microdata while preserving privacy. The microdata can change between publications via additions, deletions, insertions, and updates. There are numerous proposals for different database types, adversaries, attacks, and notions. However, many anonymization algorithms include notions of privacy and adversarial models that are specific to the context, with their own terminology and notation. Unfortunately, these proposals are difficult to generalize or translate them to other contexts complicating their understanding and comparison. To address these issues, we propose a taxonomy of anonymization technologies, compare existing solutions, and develop a unifying framework that not only harmonizes concepts and terminology but also notation and nomenclature. We analyze the current state of the art and recent advances in the literature. The analysis enables us to understand the significance and appropriateness of the various proposals in achieving privacy., Javier Parra-Arnau is the recipient of a “Ramón y Cajal” fellowship (ref. RYC2021-034256-I) funded y the Spanish Ministry of Science and Innovation and the European Union– “NextGenerationEU”/PRTR (Plan de Recuperación, Transformación y Resiliencia). This work was also supported by the Spanish Government under the project “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” PID2020-113795RB-C31, funded by MCIN/AEI/10.13039/501100011033, and through the project “MOBILYTICS” (TED2021-129782B-I00), funded by MCIN/AEI/10.13039/501100011033 and the European Union “NextGenerationEU”/PRTR., Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Privacy-centered authentication: a new framework and analysis

  • Robles González, Antonio
  • Arias Cabarcos, Patricia
  • Parra Arnau, Javier
© 2023 Elsevier. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/, The usage of authentication schemes is increasing in our daily life with the ubiquitous spreading Internet services. The verification of user’s identity is still predominantly password-based, despite of being susceptible to various attacks and openly hated by users. Bonneau et al. presented a framework, based on Usability, Deployability, and Security criteria (UDS), to evaluate authentication schemes and find a replacement for passwords. Although the UDS framework is a mature and comprehensive evaluation framework and has been extended by other authors, it does not analyse privacy aspects in the usage of authentication schemes. In the present work, we extend the UDS framework with a privacy category to allow a more comprehensive evaluation, becoming an UDSP framework. We provide a thorough, rigorous assessment of sample authentication schemes, including analyse novel behavioural biometrics. Our work also discusses implementation aspects regarding the new privacy dimension and sketches the prospect of future authentication schemes., Javier Parra-Arnau is the recipient of a “Ramón y Cajal” fellowship (ref. RYC2021–034256-I) funded by the Spanish Ministry of Science and Innovation and the European Union – “NextGenerationEU”/PRTR (Plan de Recuperación, Transformación y Resiliencia). This work was also supported by the Spanish Government under the project “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” PID2020–113795RB-C31, funded by MCIN/AEI/10.13039/501100011033, and through the project “MOBILYTICS” (TED2021–129782B-I00), funded by MCIN/AEI/10.13039/501100011033 and the European Union “NextGenerationEU”/PRTR., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

G-3MRP: a game-theoretical multimedia multimetric map-aware routing1 protocol for vehicular ad hoc networks

  • Mohamad Mezher, Ahmad
  • Aguilar Igartua, Mónica
© 2022 Elsevier. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/, The particular requirements and special features of vehicular ad hoc networks (VANETs) (e.g., special mo8 bility patterns, short link lifetimes, rapid topology changes) involve challenges for the research community. 9 One of these challenges is the development of new routing protocols specially designed for VANETs. In 10 this paper, we present a novel game-theoretical approach of a multimetric geographical routing protocol for 11 VANETs to forward video-reporting messages in smart cities. Game theory is considered a very interesting 12 theoretical framework to analyze and optimize resource allocation problems in digital communication sce13 narios. Our contribution has shown to enhance the overall performance of VANETs in urban scenarios, in 14 terms of percentage of packet losses, average end-to-end packet delay and peak signal to noise ratio (PSNR)., This work was supported by the Spanish Government under research project “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” PID2020-113795RB-C31, funded by MCIN/AEI/10.13039/501100011033. Ahmad M. Mezher holds a McCain Postdoctoral Fellowship in Innovation with the Electrical and Computer Engineering department at the University of New Brunswick (UNB), Canada ., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Uncoordinated syntactic privacy: a new composable metric for multiple, independent data publishing

  • Tobar Nicolau, Adrián
  • Parra Arnau, Javier
  • Forné Muñoz, Jorge
  • Torra, Vicenç
A privacy model is a privacy condition, dependent on a parameter, that guarantees an upper bound on the risk of reidentification disclosure and maybe also on the risk of attribute disclosure by an adversary. A privacy model is composable if the privacy guarantees of the model are preserved, possibly to a limited extent, after repeated independent application of the privacy model. From the opposite perspective, a privacy model is not composable if multiple independent data releases, each of them satisfying the requirements of the privacy model, may result in a privacy breach. Current privacy models are broadly classified into syntactic ones (such as k-anonymity and l-diversity) and semantic ones, which essentially refer to e -differential privacy (e-DP) and variations thereof. While e-DP and its variants offer strong composability properties, syntactic notions are not composable unless data releases are conducted by a single, centralized data holder that uses specialized notions such as m-invariance and t -safety. In this work, we propose m-uncoordinated-syntactic-privacy (m-USP), the first syntactic notion with composability properties for the independent publication of nondisjoint data, in other words, without a centralized data holder. Theoretical results are formally proven, and experimental results demonstrate that the risk to individuals does not increase significantly, in contrast to non-composable methods, that are susceptible to attribute disclosure. In most cases, the utility degradation caused by the extra protection is less than 5% and decreases as the value of m increases., Javier Parra-Arnau is the recipient of a “Ram´ on y Cajal” fellowship (ref. RYC2021-034256-I) funded by the Spanish Ministry of Science and Innovation and the European Union– “NextGenerationEU”/PRTR (Plan de Recuperaci´ on, Transformaci´ on y Resiliencia). This work was also supported by the Spanish Government under the following projects: ”DIstributed Smart Communications with Verifiable EneRgy-optimal Yields (DISCOVERY)” PID2023-148716OB-C32, funded by MCIN/AEI/10.13039/501100011033; “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE)” PID2020-113795RBC31, funded by MICIU/AEI/10.13039/501100011033; and “Anonymization technology for AI-based analytics of mobility data (MOBILYTICS)” (TED2021-129782B-I00), funded by MICIU/AEI/10.13039/501100011033 and by the European Union NextGenerationEU/PRTR. This work was also partially funded by the Generalitat de Catalunya, under AGAUR grant “2021 SGR 01413”; was partially supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation; and received support by the project ”Privacy for complex data” (VR 2022-04645)., Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Generación sintética de trayectorias mediante aprendizaje profundo con garantías de privacidad diferencial

  • Rubio Jornet, Víctor
  • Parra Arnau, Javier
  • Forné Muñoz, Jorge
La generación sintética de trayectorias es cru- cial para poder realizar estudios y análisis en diferentes campos, como la movilidad urbana, los protocolos de redes móviles, la epidemiología computacional o la simulación de cambios en la movilidad para la planificación urbana. Actual- mente, se ha observado que la generación de datos sintéticos sin protección adicional puede poner en riesgo la privacidad de los usuarios, dado que los modelos de aprendizaje profundo actuales son ataques de inferencia de membresía. un modelo de aprendizaje profundo ya existente llamado MoveSim, el cual genera datos sintéticos Este modelo ha sido modificado ferencialmente privado y, de esta manera, garantizar la privacidad de los usuarios que han proporcionado sus datos sin perder un rendimiento sustancial del modelo., Javier Parra-Arnau es el beneficiario de una beca Ramón y Cajal (ref. RYC2021-034256-1) financiada por el Ministerio de Ciencia e Innovación de España y la Unión Europea - "NextGenerationEU”/PRTR (Plan de Recuperación, Transformación y Resiliencia). Este trabajo también ha sido apoyado por el Gobierno español a través del proyecto “Enhancing Communication Protocols with Machine Learning while Protecting Sensitive Data (COMPROMISE” PID2020-113795RB-C31, financiado por MCIN/AEI/10.13039/501100011033, y a través del proyecto "MOBILYTICS” (TED2021-129782B-100), financiado por MCIN/AE1/10.13039/501100011033 y la Unión Europea "NextGenerationEU”/PRTR y financiado por la Generalitat de Catalunya mediante la beca AGAUR 72021 SGR 01413”., Peer Reviewed, Postprint (published version)