DecoyTrace: תחבולות רעות להגנה פעילה בלמידת מכונה מאולתרת

תקציר מקורי באנגליתarXiv:2609.36330v1 Announce Type: cross Abstract: Decentralized Federated Learning (DFL) eliminates the central aggregation server, reducing the single point of observation that traditional defenses against attacks rely on. As a result, peer-to-peer networks become exposed to malicious updates containing backdoors or semantic poisoning, since such updates can remain close to benign ones in the parameter space while behaving very differently. This may evade defenses based on passive parameter inspection. However, existing deception-based defenses have mainly been designed for centralized FL and do not jointly address local observation, poisoning propagation, source attribution, and containment in strictly serverless DFL. To address these limitations, this paper presents DecoyTrace, a proact