Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 5
Encontrada(s) 1 página(s)

RUA. Repositorio Institucional de la Universidad de Alicante
Publication Otros (Other)

When Privacy Helps: Pseudonymisation as a Strategy for Improved Cyber Incident Classification

  • Haughton, Loya C.
  • Fidalgo, Eduardo
  • Alaiz-Rodríguez, Rocío
  • Castejón-Limas, Manuel
  • Fernández-Robles, Laura
Organisations often rely on Cyber Threat Intelligence (CTI) for collective defence against evolving threats. Therefore, it is important that these shared reports are both compliant with data protection legislation and analytically useful. Pseudonymisation is a recognised data protection measure, yet its effect on downstream utility remains underexplored in cybersecurity. Unlike other domains where personal identifiers carry predictive value, personal data in cyber incident reports may act as noise rather than signal — suggesting pseudonymisation could improve classification accuracy. This hypothesis is evaluated in two steps. First, we derive three new datasets by applying Data Masking, Data Tokenisation and Data Substitution to a subset of the CECILIA-10C-900 dataset. We then evaluate 21 models — spanning traditional Machine Learning (ML) classifiers, encoder transformers and QLoRA fine-tuned Large Language Models (LLMs) — on these datasets, for a CTI classification task based on the Spanish National Cybersecurity Institute’s incident taxonomy. The RoBERTa-base model achieved the highest overall weighted F1-score of 87.35% when Data Tokenisation was applied, while Llama-3.1-8B demonstrated the largest gain (+12.63 pp) with Data Masking. These findings reframe pseudonymisation from only a compliance measure into a preprocessing step that may simultaneously protect privacy and improve classification in specific model-technique pairings.
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Otros (Other)

ANJANA

  • Sáinz-Pardo Díaz, Judith
  • López-García, Álvaro
Anjana is an open source Python library for anonymizing sensitive tabular data. Different techniques are implemented, such as: k-anonymity, (α,k)-anonymity, ℓ-diversity, entropy ℓ-diversity, recursive (c,ℓ)-diversity, t-closeness, basic β-likeness, enhanced β-likeness and δ-disclosure privacy., This work is funded by European Union through the SIESTA project (Horizon Europe) under Grant number 101131957., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Otros (Other)

Enhancing the convergence of federated learning aggregation strategies with limited data

  • Sáinz-Pardo Díaz, Judith
  • López-García, Álvaro
Trabajo presentado a la 3rd IEEE International Conference on Federated Learning Technologies and Applications (FLTA25), celebrada en Dubrovnik, Croatia del 14 al 17 de octubre de 2025., The development of deep learning techniques is a leading field applied to cases in which medical data is used, particularly in cases of image diagnosis. This type of data has privacy and legal restrictions that in many cases prevent it from being processed from central servers. However, in this area collaboration between different research centers, in order to create models as robust as possible, trained with the largest quantity and diversity of data available, is a critical point to be taken into account. In this sense, the application of privacy aware distributed architectures, such as federated learning arises. When applying this type of architecture, the server aggregates the different local models trained with the data of each data owner to build a global model. This point is critical and therefore it is fundamental to analyze different ways of aggregation according to the use case, taking into account the distribution of the clients, the characteristics of the model, etc. In this paper we propose a novel aggregation strategy and we apply it to a use case of cerebral magnetic resonance image classification. In this use case the aggregation function proposed manages to improve the convergence obtained over the rounds of the federated learning process in relation to different aggregation strategies classically implemented and applied., We would like to thank the funding and support from the AI4EOSC project and from the EOSC-SIESTA project (funded by the European Union (Horizon Europe) under grant agreement numbers 101058593 and 101131957 respectively)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Otros (Other)

Privacy preserving machine learning workflow: from anonymization to personalized differential privacy budgets in federated learning

  • Sáinz-Pardo Díaz, Judith
  • López-García, Álvaro
Date of Conference: 09-12 June 2026., Conference Location: Valencia, Spain., arXiv:2605.02372v1: Accepted at the 2nd International Conference on Federated Learning and Intelligent Computing Systems (FLICS2026)., The growing development of artificial intelligence based solutions, together with privacy legislation, has driven the rise of the so-called privacy preserving machine learning architectures, such as federated learning. While federated learning enables model training on decentralized data preventing their sharing and centralization, it still faces several challenges related to data integrity and privacy. This paper presents a comprehensive privacy preserving federated learning workflow for sensitive tabular data, including anonymization and differential privacy techniques. We also introduce a formal definition for the concept of client drift, together with ways of detecting it to mitigate poisoning attacks. Then, we detail a complete methodology for assigning personalized privacy budgets for global differential privacy to the different clients participating in the network, based on a re-identification risk metric. The proposed methodology is presented and tested on an openly available dataset of medical records. Within the experimental setup we show that the approach based on personalized budgets, compared to the architecture including global differential privacy with fixed privacy budget, achieves a better model performance in terms of two error metrics., The authors would like to thank the funding through the EOSC SIESTA project "Secure Interactive Environments for Sensitive daTa Analytics" that has received funding from the European Union’s Horizon Europe research and innovation programme under grant agreement number 101131957., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Otros (Other)

Proyecto SIESTA: uso de entornos confiables para investigación con datos sensibles

  • Rodríguez González, David
Encuentro organizado por la PTI Ciencia e Innovación Digital con el soporte del departamento de Postgrado del CSIC en la sede de Santander de la Universidad Internacional Menéndez Pelayo. 24-26 de agosto del 2026, Santander, Cantabria., Dirección: Helena Lozano, Gestora de estrategia científica CSIC, Coordinadora ejecutiva PTI Ciencia Digital., Taller sobre protección de las comunicaciones en entornos clínicos, en el que se presenta un sensor óptico para la monitorización de señales biomédicas y un sistema experimental para su transmisión. Se analiza, mediante una demostración práctica, la vulnerabilidad de estas comunicaciones ante la interceptación y manipulación de información sensible, incluyendo la generación de señales falsas que pueden provocar alarmas incorrectas. Finalmente, se muestra cómo la aplicación de mecanismos de cifrado y autenticación de los extremos protege la comunicación, garantizando la confidencialidad e integridad de las señales transmitidas., SIESTA está financiado por el programa Horizon Europe de la Unión Europea, convenio de subvención nº 101131957., 1. El problema de los datos sensibles.-- 2. El proyecto SIESTA.-- 3. Anonimizar los datos.-- 4. Cinco casos de uso.-- 5. Usabilidad de SIESTA., Peer reviewed