Print Email Facebook Twitter Client self-defense against model poisoning in federated learning Title Client self-defense against model poisoning in federated learning Author Zhu, Chaoyi (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Chen, Lydia Y. (mentor) Erkin, Z. (graduation committee) Al-Ars, Z. (graduation committee) Roos, S. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science Date 2023-06-14 Abstract Federated Learning is highly susceptible to backdoor and targeted attacks as participants can manipulate their data and models locally without any oversight on whether they follow the correct process. There are a number of server-side defenses that mitigate the attacks by modifying or rejecting local updates submitted by clients. However, we find that bursty adversarial patterns with a high variance in the number of malicious clients can circumvent the existing defenses. We propose a client-self defense, LeadFL, that is combined with existing server-side defenses to thwart backdoor and targeted attacks. The core idea of LeadFL is a novel regularization term in local model training such that the Hessian matrix of local gradients is nullified. We provide the convergence analysis of LeadFL and its robustness guarantee in terms of certified radius. Our empirical evaluation shows that LeadFL is able to mitigate bursty adversarial patterns for both iid and non-iid data distributions. It frequently reduces the backdoor accuracy from more than 75% for state-of-the-art defenses to less than 10% while its impact on the main task accuracy is always less than for other client-side defenses. Subject Federated LearningPoisoning attackFederated Averaging To reference this document use: http://resolver.tudelft.nl/uuid:44963ca4-46f8-49a1-9285-1c01e4d49402 Part of collection Student theses Document type master thesis Rights © 2023 Chaoyi Zhu Files PDF C.Zhu_thesis.pdf 3.28 MB Close viewer /islandora/object/uuid:44963ca4-46f8-49a1-9285-1c01e4d49402/datastream/OBJ/view