Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 18
Encontrada(s) 1 página(s)

Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Contribución de congreso (ConferenceOutput)

FRCSyn challenge at WACV 2024: Face recognition challenge in the era of synthetic data

  • Melzi, Pietro
  • Vera Rodríguez, Rubén
  • Morales Moreno, Aythami
  • Fiérrez Aguilar, Julián
  • Ortega García, Javier
  • Tolosana Moranchel, Rubén
  • Andrés Tamé, Iván Ioel de
Artículo escrito por un elevado número de autores, solo se referencian el que aparece en primer lugar, el nombre del grupo de colaboración, si le hubiere, y los autores pertenecientes a la UAM, Despite the widespread adoption of face recognition technology around the world, and its remarkable performance on current benchmarks, there are still several challenges that must be covered in more detail. This paper offers an overview of the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn) organized at WACV 2024. This is the first international challenge aiming to explore the use of synthetic data in face recognition to address existing limitations in the technology. Specifically, the FRCSyn Challenge targets concerns related to data privacy issues, demographic biases, generalization to unseen scenarios, and performance limitations in challenging scenarios, including significant age disparities between enrollment and testing, pose variations, and occlusions. The results achieved in the FRCSyn Challenge, together with the proposed benchmark, contribute significantly to the application of synthetic data to improve face recognition technology., This study has received funding from the European Union's Horizon 2020 TReSPAsS-ETN (No 860813) and is supported by INTER-ACTION (PID2021- 126521OB-100 MICINN/FEDER) and R&D Agreement DGGC/UAM/FUAM for Biometrics and Cybersecurity. It is also supported by the German Federal Ministry of Education and Research and the Hessian Ministry of Higher Education, Research, Science and the Arts within their joint support of the National Research Center for Applied Cybersecurity ATHENE. MeVer was supported by the EU Horizon Europe project MAMMOth (Grant Agreement 101070285)
Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Contribución de congreso (ConferenceOutput)

Keystroke Biometrics in Response to Fake News Propagation in a Global Pandemic

  • Morales Moreno, Aythami
  • Fiérrez Aguilar, Julián
  • Vera Rodríguez, Rubén
  • Ortega García, Javier
  • Tolosana Moranchel, Rubén
  • Acién Ayala, Alejandro
  • Monaco, John V.
© 2020 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, This work proposes and analyzes the use of keystroke biometrics for content de-anonymization. Fake news have become a powerful tool to manipulate public opinion, especially during major events. In particular, the massive spread of fake news during the COVID-19 pandemic has forced governments and companies to fight against missinformation. In this context, the ability to link multiple accounts or profiles that spread such malicious content on the Internet while hiding in anonymity would enable proactive identification and blacklisting. Behavioral biometrics can be powerful tools in this fight. In this work, we have analyzed how the latest advances in keystroke biometric recognition can help to link behavioral typing patterns in experiments involving 100,000 users and more than 1 million typed sequences. Our proposed system is based on Recurrent Neural Networks adapted to the context of content de-anonymization. Assuming the challenge to link the typed content of a target user in a pool of candidate profiles, our results show that keystroke recognition can be used to reduce the list of candidate profiles by more than 90%. In addition, when keystroke is combined with auxiliary data (such as location), our system achieves a Rank-1 identification performance equal to 52.6% and 10.9% for a background candidate list composed of 1K and 100K profiles, respectively, This work has been supported by projects: PRIMA (MSCA-ITN-2019-860315), TRESPASS (MSCA-ITN-2019-860813), BIBECA (RTI2018-101248-B-I00 MINECO), BioGuard (Ayudas Fundacion BBVA a Equipos de Investigacion Cientıfica 2017). A. Acien and R. Tolosana are supported by a FPI and postdoc fellowship from the Spanish MINECO
Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Contribución de congreso (ConferenceOutput)

MEBAL: A multimodal database for eye blink detection and attention level estimation

  • Daza García, Roberto
  • Morales Moreno, Aythami
  • Fiérrez Aguilar, Julián
  • Tolosana Moranchel, Rubén
© ACM 2020. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in ICMI '20 Companion, October 25–29, 2020, Virtual Event, Netherlands, https://doi.org/10.1145/3395035.3425257, This work presents mEBAL, a multimodal database for eye blink detection and attention level estimation. The eye blink frequency is related to the cognitive activity and automatic detectors of eye blinks have been proposed for many tasks including attention level estimation, analysis of neuro-degenerative diseases, deception recognition, drive fatigue detection, or face anti-spoofing. However, most existing databases and algorithms in this area are limited to experiments involving only a few hundred samples and individual sensors like face cameras. The proposed mEBAL improves previous databases in terms of acquisition sensors and samples. In particular, three different sensors are simultaneously considered: Near Infrared (NIR) and RGB cameras to capture the face gestures and an Electroencephalography (EEG) band to capture the cognitive activity of the user and blinking events. Regarding the size of mEBAL, it comprises 6,000 samples and the corresponding attention level from 38 different students while conducting a number of e-learning tasks of varying difficulty. In addition to presenting mEBAL, we also include preliminary experiments on: i) eye blink detection using Convolutional Neural Networks (CNN) with the facial images, and ii) attention level estimation of the students based on their eye blink frequency, This work has been supported by projects: PRIMA (ITN-2019-860315), TRESPASS-ETN (ITN-2019-860813), IDEA-FAST (IMI2- 2018-15-two-stage-853981), BIBECA (RTI2018-101248-B-I00 MINECOFEDER), and edBB (Universidad Autonoma de Madrid). Ruben Tolosana and postdoc support from CAM/FEDER. Roberto Daza is supported by a PhD FPI fellowship from MINECO-FEDER
Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Contribución de congreso (ConferenceOutput)

SaFL: Sybil-aware Federated Learning with application to face recognition

  • Ghafourian, Mahdi
  • Fiérrez Aguilar, Julián
  • Vera Rodríguez, Rubén
  • Morales Moreno, Aythami
  • Tolosana Moranchel, Rubén
© 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, Federated Learning (FL) is a machine learning paradigm to conduct collaborative learning among clients on a joint model. The primary goal is to share clients' local training parameters with an integrating server while preserving their privacy. This method permits to exploit the potential of massive mobile users' data for the benefit of machine learning models' performance while keeping sensitive data on local devices. On the downside, FL raises security and privacy concerns that have just started to be studied. To address some of the key threats in FL, researchers have proposed to use secure aggregation methods (e.g. homomorphic encryption, secure multiparty computation, etc.). These solutions improve some security and privacy metrics, but at the same time bring about other serious threats such as poisoning attacks, backdoor attacks, and free running attacks. This paper proposes a new defense method against poisoning attacks in FL called SaFL (Sybil-Aware Federated Learning) that minimizes the effect of sybils with a novel time-variant aggregation scheme, This work has been supported by projects: PRIMA (ITN-2019-860315), TRESPASS-ETN (ITN-2019-860813) and Cátedra ENIA UAM-VERIDAS en IA Responsable (NextGenerationEU PRTR TSI-100927-2023-2)
Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Contribución de congreso (ConferenceOutput)

A Comparative Evaluation of Heart Rate Estimation Methods using Face Videos

  • Hernández Ortega, Javier
  • Diaz, David
  • Fiérrez Aguilar, Julián
  • Morales Moreno, Aythami
© 2020 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, This paper presents a comparative evaluation of methods for remote heart rate estimation using face videos, i.e., given a video sequence of the face as input, methods to process it to obtain a robust estimation of the subject's heart rate at each moment. Four alternatives from the literature are tested, three based in hand-crafted approaches and one based on deep learning. The methods are compared using RGB videos from the COHFACE database. Experiments show that the learning-based method achieves much better accuracy than the hand-crafted ones. The low error rate achieved by the learning-based model makes possible its application in real scenarios, e.g. in medical or sports environments, This work has been supported by projects: IDEAFAST (IMI2-2018-15-two-stage-853981), PRIMA (ITN-2019-860315), TRESPASS-ETN (ITN-2019-860813), BIBECA (RTI2018- 101248-B-I00 MINECO/FEDER), and edBB (UAM). J.H.O. is supported by a PhD Scholarship from UAM. Portions of the research in this paper used the COHFACE Dataset made available by the Idiap Research Institute, Martigny, Switzerland
Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Contribución de congreso (ConferenceOutput)

Assessing the quality of swipe interactions for mobile biometric systems

  • Santopietro, Marco
  • Guest, Richard
  • Acién Ayala, Alejandro
  • Vera Rodríguez, Rubén
  • Morales Moreno, Aythami
© 2020 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, Quality estimation is a key study in biometrics, allowing optimisation and improvement of existing authentication systems by giving a prediction on the model performance based on the goodness of the sample or the user. In this paper, we propose a quality metric for swipe gestures on mobile devices. We evaluate a quality score for subjects on enrollment and for swipe samples, we estimate three quality groups and explore the correlation between our quality score and a state-of-art biometric authentication classifier performance. A further analysis based on the combined effects of subject quality and the amount of enrollment samples is conducted, investigating if increasing or decreasing enrollment size affects the authentication performance for different quality groups. Results are shown for three different public datasets, highlighting how higher quality users score a lower equal error rate compared to medium and low quality users, while high quality samples get a higher similarity score from the classifier, Thanks to support by projects: PRIMA (H2020-MSCAITN-2019-860315), TRESPASS-ETN (H2020-MSCAITN-2019-860813), BIBECA (RTI2018-101248-B-I00 MINECO/FEDER), and BioGuard (Ayudas Fundacion BBVA a Equipos de Investigacion Científica 2017)
Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Contribución de congreso (ConferenceOutput)

SDFR: Synthetic Data for Face Recognition competition

  • Shahreza, Hatef Otroshi
  • Vera Rodríguez, Rubén
  • Fiérrez Aguilar, Julián
  • Tolosana Moranchel, Rubén
  • Andrés Tamé, Iván Ioel de
Artículo escrito por un elevado número de autores, solo se referencian el que aparece en primer lugar, el nombre del grupo de colaboración, si le hubiere, y los autores pertenecientes a la UAM, Large-scale face recognition datasets are collected by crawling the Internet and without individuals' consent, raising legal, ethical, and privacy concerns. With the recent advances in generative models, recently several works proposed generating synthetic face recognition datasets to mitigate concerns in web-crawled face recognition datasets. This paper presents the summary of the Synthetic Data for Face Recognition (SDFR) Competition held in conjunction with the 18th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2024) and established to investigate the use of synthetic data for training face recognition models. The SDFR competition was split into two tasks, allowing participants to train face recognition systems using new synthetic datasets and/or existing ones. In the first task, the face recognition backbone was fixed and the dataset size was limited, while the second task provided almost complete freedom on the model backbone, the dataset, and the training pipeline. The submitted models were trained on existing and also new synthetic datasets and used clever methods to improve training with synthetic data. The submissions were evaluated and ranked on a diverse set of seven benchmarking datasets. The paper gives an overview of the submitted face recognition models and reports achieved performance compared to baseline models trained on real and synthetic datasets. Furthermore, the evaluation of submissions is extended to bias assessment across different demography groups. Lastly, an outlook on the current state of the research in training face recognition models using synthetic data is presented, and existing problems as well as potential future directions are also discussed, The organization of this competition was supported by the H2020 TReSPAsS-ETN Marie Skłodowska-Curie early training network (grant agreement 860813) as well as the Hasler foundation through the “Responsible Face Recognition” (SAFER) project. The work of BioLab team received funding from the European Union's Horizon 2020 research and innovation program under Grant Agreement No. 883356. The submitted solution by the IGD-IDiff-Face team has been funded by the German Federal Ministry of Education and Research and the Hessian Ministry of Higher Education, Research, Science and the Arts within their joint support of the National Research Center for Applied Cybersecurity ATHENE. The work of BiDA-PRA team was supported by INTER-ACTION (PID2021-1265210B-I00 MICINN/FEDER), Cátedra ENIA UAM-VERIDAS en IA Responsable (NextGenerationEU PRTR TSI-100927-2023-2), and R&D Agreement DGGC/UAM/FUAM for Biometrics and Cybersecurity. The work of BiDA-PRA team was also supported by the European Union - Next Generation EU through the Italian Ministry of University and Research (MUR) within the PRIN PNRR 2022 - BullyBuster 2 - the ongoing fight against bullying and cyberbullying with the help of artificial intelligence for the human wellbeing (CUP: F53D23009240001)
Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Contribución de congreso (ConferenceOutput)

Fishing gear classification from vessel trajectories and velocity profiles: database and benchmark

  • Melzi, Pietro
  • Rodriguez-Albala, Juan Manuel
  • Morales Moreno, Aythami
  • Fiérrez Aguilar, Julián
  • Vera Rodríguez, Rubén
  • Tolosana Moranchel, Rubén
International Organizations demand to take care of our oceans and their ecosystems since they are of incalculable value to humanity. The illegal fishing activity does irreparable damage to these ecosystems and these organism are pushing to detect and combat illegal fishing activities. Fishing vessels are equipped with a radio frequency beacon that emits their GPS position and other information relevant to the Automatic Identification System (AIS). The GPS positions can be used to infer the vessel trajectories and detect illegal fishing activities. In this study we present a new database (https://github.com/BiDAlab/TrFGdb ) including trajectories representing 5 different fishing gears, and analyze them as in a problem of time sequence analysis. We extract global and local features from the trajectories of vessels, and propose several supervised learning algorithms to classify the kinematics of vessels according to different fishing gears. Compared to previous works, we highlight the importance of considering trajectories with sampling period in the order of minutes instead of hours, to detect activities carried out in a short time that could help to distinguish fishing gears. A considerable effort has been dedicated to pre-processing the real data at our disposal, to generate a quality dataset with highly reliable labels. The best classification accuracy obtained in this study is 90%. We expect to improve it if more trajectories describing the different fishing gears were available, We thank Tragsatec’s Management of Agricultural and Fisheries Information Systems and the General Secretariat of Fisheries of the Spanish Ministry of Agriculture, Fisheries and Food for the data and expertise provided to carry out the study. This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Sk lodowska-Curie grant agreement No 860813 - TReSPAsS-ETN. This study is also supported by the project INTER-ACTION (PID2021- 126521OB-I00 MICINN/FEDER)
Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Contribución de congreso (ConferenceOutput)

Second edition FRCSyn challenge at CVPR 2024: Face recognition challenge in the era of synthetic data

  • DeAndres-Tame, Ivan
  • Melzi, Pietro
  • Vera Rodríguez, Rubén
  • Morales Moreno, Aythami
  • Fiérrez Aguilar, Julián
  • Ortega García, Javier
  • Tolosana Moranchel, Rubén
”Artículo escrito por un elevado número de autores, solo se referencian el que aparece en primer lugar, el nombre del grupo de colaboración, si le hubiere, y los autores pertenecientes a la UAM”, “© 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”, Synthetic data is gaining increasing relevance for training machine learning models. This is mainly motivated due to several factors such as the lack of real data and intraclass variability, time and errors produced in manual labeling, and in some cases privacy concerns, among others. This paper presents an overview of the 2nd edition of the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn) organized at CVPR 2024. FRCSyn aims to investigate the use of synthetic data in face recognition to address current technological limitations, including data privacy concerns, demographic biases, generalization to novel scenarios, and performance constraints in challenging situations such as aging, pose variations, and occlusions. Unlike the 1st edition, in which synthetic data from DCFace and GANDiffFace methods was only allowed to train face recognition systems, in this 2nd edition we propose new subtasks that allow participants to explore novel face generative methods. The outcomes of the 2nd FRCSyn Challenge, along with the proposed experimental protocol and benchmarking contribute significantly to the application of synthetic data to face recognition, This study has received funding from the European Union’s Horizon 2020 TReSPAsS-ETN (No 860813) and is supported by INTER-ACTION (PID2021-126521OB-I00 MICINN/FEDER), Catedra ENIA UAM-VERIDAS en IA Responsable (NextGenerationEU PRTR TSI-100927-2023-2) and R&D Agreement DGGC/ UAM/FUAM for Biometrics and Cybersecurity. It is also supported by the German Federal Ministry of Education and Research and the Hessian Ministry of Higher Education, Research, Science and the Arts within their joint support of the National Research Center for Applied Cybersecurity ATHENE. K-IBS-DS was supported by the Institute for Basic Science, Republic of Korea (IBS-R029-C2). UNICA-IGD-LSI was supported by the ARIS program P2-0250B
Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Contribución de congreso (ConferenceOutput)

PAD-Phys: Exploiting physiology for presentation attack detection in face biometrics

  • Gómez, Luis F.
  • Solano, Imanol
  • Garcia, Alejandro
  • Zamora-Martinez, Francisco
  • Fiérrez Aguilar, Julián
  • Morales Moreno, Aythami
  • Tolosana Moranchel, Rubén
  • Ghafourian, Mahdi
Presentation Attack Detection (PAD) is a crucial stage in facial recognition systems to avoid leakage of personal information or spoofing of identity to entities. Recently, pulse detection based on remote photoplethysmography (rPPG) has been shown to be effective in face presentation attack detection. This work presents three different approaches to the presentation attack detection based on rPPG: (i) The physiological domain, a domain using rPPG-based models, (ii) the Deepfakes domain, a domain where models were retrained from the physiological domain to specific Deepfakes detection tasks; and (iii) a new Presentation Attack domain was trained by applying transfer learning from the two previous domains to improve the capability to differentiate between bona-fides and attacks. The results show the efficiency of the rPPG-based models for presentation attack detection, evidencing a 21.70% decrease in average classification error rate (ACER) (from 41.03% to 19.32%) when the presentation attack domain is compared to the physiological and Deepfakes domains. Our experiments highlight the efficiency of transfer learning in rPPG-based models and perform well in presentation attack detection in instruments that do not allow copying of this physiological feature, This work has been supported by Veridas and by projects: TRESPASS-ETN (ITN-2019-860813), PRIMA (ITN2019-860315), and BBforTAI (PID2021-127641OB-I00 MICINN/FEDER)
Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Contribución de congreso (ConferenceOutput)

Learning emotional-blinded face representations

  • Peña Almansa, Alejandro
  • Lapedriza, Agata
  • Fiérrez Aguilar, Julián
  • Morales Moreno, Aythami
© 2021 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, We propose two face representations that are blind to facial expressions associated to emotional responses. This work is in part motivated by new international regulations for personal data protection, which enforce data controllers to protect any kind of sensitive information involved in automatic processes. The advances in Affective Computing have contributed to improve human-machine interfaces but, at the same time, the capacity to monitorize emotional responses triggers potential risks for humans, both in terms of fairness and privacy. We propose two different methods to learn these expression-blinded facial features. We show that it is possible to eliminate information related to emotion recognition tasks, while the performance of subject verification, gender recognition, and ethnicity classification are just slightly affected. We also present an application to train fairer classifiers in a case study of attractiveness classification with respect to a protected facial expression attribute. The results demonstrate that it is possible to reduce emotional information in the face representation while retaining competitive performance in other face-based artificial intelligence tasks, This work has been supported by projects: PRIMA (H2020-MSCA-ITN-2019-860315), TRESPASS-ETN (H2020-MSCAITN-2019-860813), IDEA-FAST (IMI2-2018-15-853981), BIBECA (RTI2018-101248-B-I00 MINECO/FEDER), REAVIPERO (RED2018-102511-T), RTI2018-095232-B-C22 MINECO, and Accenture. A. Pena is supported by a research fellowship (PEJ2018-004094A) from the Spanish MINECO
Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Contribución de congreso (ConferenceOutput)

Multi-IVE: privacy enhancement of multiple soft-biometrics in face embeddings

  • Melzi, Pietro
  • Shahreza, Hatef Otroshi
  • Rathgeb, Christian
  • Marcel, Sébastien
  • Busch, Christoph
  • Vera Rodríguez, Rubén
  • Fiérrez Aguilar, Julián
  • Tolosana Moranchel, Rubén
This study focuses on the protection of soft-biometric at-tributes related to the demographic information of individ-uals that can be extracted from compact representations of face images, called embeddings. We consider a state-of-the-art technology for soft-biometric privacy enhancement, Incremental Variable Elimination (IVE), and propose Multi-IVE, a new method based on IVE to secure multiple soft-biometric attributes simultaneously. Several aspects of this technology are investigated, proposing different approaches to effectively identify and discard multiple soft-biometric at-tributes contained in face embeddings. In particular, we consider a domain transformation using Principle component Analysis (PCA), and apply IVE in the PCA domain. A complete analysis of the proposed Multi-IVE algorithm is carried out studying the embeddings generated by state-of-the-art face feature extractors, predicting soft-biometric attributes contained within them with multiple machine learning classifiers, and providing a cross-database evaluation. The results obtained show the possibility to simultane-ously secure multiple soft-biometric attributes and support the application of embedding domain transformations be-fore addressing the enhancement of soft-biometric privacy, This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 860813 - TReSPAsS-ETN and the German Federal Ministry of Education and Research and the Hessian Ministry of Higher Education, Research, Science and the Arts within their joint support of the National Research Center for Applied Cybersecurity ATHENE. R. Tolosana and R. Vera-Rodriguez are also supported by INTERACTION (PID2021-126521OB-I00 MICINN/FEDER)
Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Contribución de congreso (ConferenceOutput)

Exploring transformers for on-line handwritten signature verification

  • Melzi, Pietro
  • Stragapede, Giuseppe
  • Vera Rodríguez, Rubén
  • Fiérrez Aguilar, Julián
  • Ortega García, Javier
  • Tolosana Moranchel, Rubén
  • Delgado Santos, Paula
The application of mobile biometrics as a user-friendly authentication method has increased in the last years. Recent studies have proposed novel behavioral biometric recognition systems based on Transformers, which currently outperform the state of the art in several application scenarios. On-line handwritten signature verification aims to verify the identity of subjects, based on their biometric signatures acquired using electronic devices such as tablets or smartphones. This paper investigates the suitability of architectures based on recent Transformers for on-line signature verification. In particular, four different configurations are studied, two of them rely on the Vanilla Transformer encoder, and the two others have been successfully applied to the tasks of gait and activity recognition. We evaluate the four proposed configurations according to the experimental protocol proposed in the SVC-onGoing competition. The results obtained in our experiments are promising, and promote the use of Transformers for on-line signature verification, This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 860813 - TReSPAsSETN. With support also from projects INTER-ACTION (PID2021-126521OB-I00 MICINN/FEDER) and HumanCAIC (TED2021-131787B-I00 MICINN)
Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Contribución de congreso (ConferenceOutput)

Blockchain in the Internet of Things: Architectures and Implementation

  • Delgado Ben Mohatar, Óscar
  • Fiérrez Aguilar, Julián
  • Morales Moreno, Aythami
  • Tolosana Moranchel, Rubén
© 2020 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., IEEE Annual International Computer Software and Applications Conference (COMPSAC) celebrado en 2020 en Madrid, The world is becoming more interconnected every day. With the high technological evolution and the increasing deployment of it in our society, scenarios based on the Internet of Things (IoT) can be considered a reality nowadays. However, and before some predictions become true (around 75 billion devices are expected to be interconnected in the next few years), many efforts must be carried out in terms of scalability and security. In this study we propose and evaluate a new approach based on the incorporation of Blockchain into current IoT scenarios. The main contributions of this study are as follows: i) an in depth analysis of the different possibilities for the integration of Blockchain into IoT scenarios, focusing on the limited processing capabilities and storage space of most IoT devices, and the eco nomic cost and performance of current Blockchain technologies; ii) a new method based on a novel module named BIoT Gateway that allows both unidirectional and bidirectional communications with IoT devices on real scenarios, allowing to exchange any kind of data; and iii) the proposed method has been fully implemented and validated on two different real-life IoT scenarios, extracting very interesting findings in terms of economic cost and execution time. The source code of our implementation is publicly available in the Ethereum testnet., This work has been supported by projects: PRIMA (H2020-MSCA-ITN-2019-860315), TRESPASS-ETN (H2020-MSCA-ITN-2019-860813), BIBECA (RTI2018- 101248-B-I00 MINECO/FEDER), and COPCIS (TIN2017- 84844-C2-1-R MINECO/FEDER). Ruben Tolosana is supported by Consejer´ıa de Educacion, Juventud y Deporte ´ de la Comunidad de Madrid y Fondo Social Europeo.
Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Contribución de congreso (ConferenceOutput)

GANDiffFace: controllable generation of synthetic datasets for face recognition with realistic variations

  • Melzi, Pietro
  • Rathgeb, Christian
  • Lawatsch, Dominik
  • Domin, Florian
  • Schaubert, Maxim
  • Vera Rodríguez, Rubén
  • Tolosana Moranchel, Rubén
Face recognition systems have significantly advanced in recent years, driven by the availability of large-scale datasets. However, several issues have recently came up, including privacy concerns that have led to the discontinuation of well-established public datasets. Synthetic datasets have emerged as a solution, even though current synthesis methods present other drawbacks such as limited intraclass variations, lack of realism, and unfair representation of demographic groups. This study introduces GAN-DiffFace, a novel framework for the generation of synthetic datasets for face recognition that combines the power of Generative Adversarial Networks (GANs) and Diffusion models to overcome the limitations of existing synthetic datasets. In GANDiffFace, we first propose the use of GANs to synthesize highly realistic identities and meet target demographic distributions. Subsequently, we fine-tune Diffusion models with the images generated with GANs, synthesizing multiple images of the same identity with a variety of accessories, poses, expressions, and contexts. We generate multiple synthetic datasets by changing GANDiffFace settings, and compare their mated and non-mated score distributions with the distributions provided by popular real-world datasets for face recognition, i.e. VGG2 and IJB-C. Our results show the feasibility of the proposed GANDiffFace, in particular the use of Diffusion models to enhance the (limited) intra-class variations provided by GANs towards the level of real-world datasets, This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 860813 - TReSPAsS-ETN. This study is supported by the project INTER-ACTION (PID2021- 126521OB-I00 MICINN/FEDER). This research is based upon work supported by the Hessian Ministry of the Interior and Sport in the course of the Bio4ensics project and by the German Federal Ministry of Education and Research and the Hessian Ministry of Higher Education, Research, Science and the Arts within their joint support of the National Research Center for Applied Cybersecurity ATHENE
Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Contribución de congreso (ConferenceOutput)

Synthetic data for the mitigation of demographic biases in face recognition

  • Melzi, Pietro
  • Rathgeb, Christian
  • Vera Rodríguez, Rubén
  • Morales Moreno, Aythami
  • Lawatsch, Dominik
  • Domin, Florian
  • Schaubert, Maxim
  • Tolosana Moranchel, Rubén
Los miembros de la UAM pertenecen al Biometrics and Data Pattern Analytics Laboratory, “© 2023 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”, This study investigates the possibility of mitigating the demographic biases that affect face recognition technologies through the use of synthetic data. Demographic biases have the potential to impact individuals from specific demographic groups, and can be identified by observing disparate performance of face recognition systems across demographic groups. They primarily arise from the unequal representations of demographic groups in the training data. In recent times, synthetic data have emerged as a solution to some problems that affect face recognition systems. In particular, during the generation process it is possible to specify the desired demographic and facial attributes of images, in order to control the demographic distribution of the synthesized dataset, and fairly represent the different demographic groups. We propose to fine-tune with synthetic data existing face recognition systems that present some demographic biases. We use synthetic datasets generated with GANDiffFace, a novel framework able to synthesize datasets for face recognition with controllable demographic distribution and realistic intra-class variations. We consider multiple datasets representing different demographic groups for training and evaluation. Also, we fine-tune different face recognition systems, and evaluate their demographic fairness with different metrics. Our results support the proposed approach and the use of synthetic data to mitigate demographic biases in face recognition, This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 860813-TReSPAsS-ETN. This study is supported by the project INTER-ACTION (PID2021-126521OB-I00 MICINN/FEDER). This research is based upon work supported by the Hessian Ministry of the Interior and Sport in the course of the Bio4ensics project and by the German Federal Ministry of Education and Research and the Hessian Ministry of Higher Education, Research, Science and the Arts within their joint support of the National Research Center for Applied Cybersecurity ATHENE
Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Contribución de congreso (ConferenceOutput)

TypeNet: Scaling up keystroke biometrics

  • Acién Ayala, Alejandro
  • Morales Moreno, Aythami
  • Vera Rodríguez, Rubén
  • Fiérrez Aguilar, Julián
  • Monaco, John V.
© 2020 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, We study the suitability of keystroke dynamics to authenticate 100 K users typing free-text. For this, we first analyze to what extent our method based on a Siamese Recurrent Neural Network (RNN) is able to authenticate users when the amount of data per user is scarce, a common scenario in free-text keystroke authentication. With 1 K users for testing the network, a population size comparable to previous works, TypeNet obtains an equal error rate of 4.8% using only 5 enrollment sequences and 1 test sequence per user with 50 keystrokes per sequence. Using the same amount of data per user, as the number of test users is scaled up to 100K, the performance in comparison to 1 K decays relatively by less than 5%, demonstrating the potential of Type-Net to scale well at large scale number of users. Our experiments are conducted with the Aalto University keystroke database. To the best of our knowledge, this is the largest free-text keystroke database captured with more than 136M keystrokes from 168K users, This work has been supported by projects: PRIMA (MSCA-ITN-2019-860315), TRESPASS (MSCAITN-2019-860813), BIBECA (RTI2018-101248-B-I00 MINECO), and by edBB (UAM). A. Acien is supported by a FPI fellowship from the Spanish MINECO
Biblos-e Archivo. Repositorio Institucional de la UAM
Publication Contribución de congreso (ConferenceOutput)

OTB-morph: One-Time Biometrics via Morphing applied to Face Templates

  • Ghafourian, Mahdi
  • Serna Cabello, José Ignacio de la
  • Fiérrez Aguilar, Julián
  • Vera Rodríguez, Rubén
  • Morales Moreno, Aythami
© 2022 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, Cancelable biometrics refers to a group of techniques in which the biometric inputs are transformed intentionally using a key before processing or storage. This transformation is repeatable enabling subsequent biometric comparisons. This paper introduces a new scheme for cancelable biometrics aimed at protecting the templates against potential attacks, applicable to any biometric-based recognition system. Our proposed scheme is based on time-varying keys obtained from morphing random biometric information. An experimental implementation of the proposed scheme is given for face biometrics. The results confirm that the proposed approach is able to withstand against leakage attacks while improving the recognition performance, This work has been supported by projects: PRIMA (ITN-2019-860315), TRESPASS-ETN (ITN-2019-860813), and BIBECA (RTI2018-101248-B-I00 MINECO/FEDER). M.G. is supported by PRIMA and I.S. is supported by a FPI fellowship from Univ. Autonoma de Madrid.