RT Conference Proceedings
T1 Defense Strategy against Byzantine Attacks in Federated Machine Learning: 												Developments towards Explainability
A1 Rodriguez-Barroso, Nuria
A1 Del Ser, Javier
A1 Luzon, M. Victoria
A1 Herrera, Francisco
AB The rise of high-risk AI systems has led to escalating concerns, prompting regulatory efforts such as the recently approved EU AI Act. In this context, the development of responsible AI systems is crucial. To this end, trustworthy AI techniques aim at requirements (including transparency, privacy awareness and fairness) that contribute to the development of responsible, robust and safe AI systems. Among them, Federated Learning (FL) has emerged as a key approach to safeguarding data privacy while enabling the collaborative training of AI models. However, FL is prone to adversarial attacks, particularly byzantine attacks, which aim to modify the behavior of the model. This work addresses this issue by proposing an eXplainable and Impartial Dynamic Defense against Byzantine Attacks (XI-DDaBA). This defense mechanism relies on robust aggregation operators and filtering techniques to mitigate the effects of adversarial attacks in FL, while providing explanations for its decisions and ensuring that clients with poor data quality are not discriminated. Experimental simulations are discussed to assess the performance of XI-DDaBA against other baselines from the literature, and to showcase its provided explanations. Overall, XI-DDaBA aligns with the need for responsible AI systems in high-risk collaborative learning scenarios through the explainable and impartial provision of robustness against attacks.
PB Institute of Electrical and Electronics Engineers Inc.
SN 9798350319545
SN 1098-7584
YR 2024
FD 2024
LK https://hdl.handle.net/11556/4817
UL https://hdl.handle.net/11556/4817
LA eng
NO Rodriguez-Barroso , N , Del Ser , J , Luzon , M V & Herrera , F 2024 , Defense Strategy against Byzantine Attacks in Federated Machine Learning : Developments towards Explainability . in 2024 IEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2024 - Proceedings . IEEE International Conference on Fuzzy Systems , Institute of Electrical and Electronics Engineers Inc. , 2024 IEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2024 , Yokohama , Japan , 30/06/24 . https://doi.org/10.1109/FUZZ-IEEE60900.2024.10611769
NO conference
NO Publisher Copyright: © 2024 IEEE.
DS TECNALIA Publications
RD 27 sept 2024