Metraipolis › archive › dc_fbe5f1014853
Optimizing Byzantine Node Placement in Decentralized Federated Learning — arXiv:2609.01495
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01495
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:34:23.763Z
- SHA-256 of the archived text
63d19143e9f6f69aba99143c7ebe25aa6a302aa3e78e97f44d6ef0cd76821c6f- Stable URL of this page
https://metraipolis.com/documento/dc_fbe5f1014853
How to cite
Optimizing Byzantine Node Placement in Decentralized Federated Learning — arXiv:2609.01495 — arXiv (en), https://arxiv.org/abs/2609.01495 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fbe5f1014853 (Metraipolis archive dc_fbe5f1014853, sha256 63d19143e9f6f69aba99143c7ebe25aa6a302aa3e78e97f44d6ef0cd76821c6f)
BibTeX
@misc{dcfbe5f1014853,
title = {Optimizing Byzantine Node Placement in Decentralized Federated Learning — arXiv:2609.01495},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01495},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fbe5f1014853; sha256 63d19143e9f6f69aba99143c7ebe25aa6a302aa3e78e97f44d6ef0cd76821c6f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01495. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Unlike placement criteria based on node centrality heuristics, BPI directly accounts for weighted multi-hop propagation and interactions among compromised nodes. We develop efficient algorithms for optimizing BPI and evaluate them across six heterogeneous graph families, untargeted model poisoning, and backdoor attacks. BPI-guided placements consistently identify highly damaging configurations across different network structures and remain effective when the linear gossip assumption is relaxed through Byzantine-robust aggregation. Our results show that Byzantine placement is a critical but under-modeled dimension of DFL threat models and robustness evaluations. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.01495 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T06:15:12.904Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).