Voyager: MTD-Based Aggregation Protocol for Mitigating Poisoning Attacks on DFL

arXiv:2310.08739v2 Announce Type: replace
Abstract: The growing concern over malicious attacks targeting the robustness of both Centralized and Decentralized Federated Learning (FL) necessitates novel defensive strategies. In contrast to the centralized approach, Decentralized FL (DFL) has the advantage of utilizing network topology and local dataset information, enabling the exploration of Moving Target Defense (MTD) based approaches.
This work presents a theoretical analysis of the influence of network topology on the robustness of DFL models. Drawing inspiration from these findings, a …

aggregation arxiv attacks cs.cr cs.dc dataset decentralized defensive federated federated learning information local malicious network novel poisoning poisoning attacks protocol robustness strategies targeting voyager