Optimizing Byzantine Node Placement in Decentralized Federated Learning
[Uczenie maszynowe] Autorzy: Edoardo Gabrielli, Gabriele Tolomei
Security evaluations of decentralized federated learning (DFL) typically focus on how Byzantine participants behave, while largely overlooking which participants are compromised. Yet, because aggregation is distributed over a communication graph, the placement of Byzantine nodes determines how malicious influence propagates through the network. We therefore treat Byzantine placement as an explicit adversarial decision and formulate the attacker's objective as selecting, under a fixed compromise budget, the set of participants that maximizes its finite-time impact on honest nodes. To approximate this objective without executing the learning process for every candidate placement, we introduce Byzantine Placement Influence (BPI), a set-level measure derived from the actual gossip dynamics that quantifies the cumulative exposure of honest nodes to Byzantine sources over the training horizon…
- Kategoria arxiv
- cs.LG
- Kategoria
- Uczenie maszynowe