Metraipolis › archive › dc_da265becce68

Hear No Evil: Detecting Gradient Leakage by Malicious Servers in Federated Learning — arXiv:2506.20651

Source: arXiv (en)
Original: https://arxiv.org/abs/2506.20651
License (as archived): CC0-1.0
Archived: 2026-11-03T07:22:09.915Z
SHA-256 of the archived text: 1d76763d86fda853783654dd8ad53f82bd233423002588b2a6c652a607c13fbd
Stable URL of this page: https://metraipolis.com/documento/dc_da265becce68

How to cite

Hear No Evil: Detecting Gradient Leakage by Malicious Servers in Federated Learning — arXiv:2506.20651 — arXiv (en), https://arxiv.org/abs/2506.20651 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da265becce68 (Metraipolis archive dc_da265becce68, sha256 1d76763d86fda853783654dd8ad53f82bd233423002588b2a6c652a607c13fbd)

BibTeX

@misc{dcda265becce68,
  title = {Hear No Evil: Detecting Gradient Leakage by Malicious Servers in Federated Learning — arXiv:2506.20651},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2506.20651},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da265becce68; sha256 1d76763d86fda853783654dd8ad53f82bd233423002588b2a6c652a607c13fbd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2506.20651. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent work has shown that gradient updates in federated learning (FL) can unintentionally reveal sensitive information about a client's local data. This risk becomes significantly greater when a malicious server manipulates the global model to provoke information-rich updates from clients. In this paper, we adopt a defender's perspective to provide the first comprehensive analysis of malicious gradient leakage attacks and the model manipulation techniques that enable them. Our investigation reveals a core trade-off: these attacks cannot be both highly effective in reconstructing private data and sufficiently stealthy to evade detection -- especially in realistic FL settings that incorporate common normalization techniques and federated averaging. Building on this insight, we argue that malicious gradient leakage attacks, while theoretically concerning, are inherently limited in practice and often detectable through basic monitoring. As a complementary contribution, we propose a simple, lightweight, and broadly applicable client-side detection mechanism that flags suspicious model updates before local training begins, despite the fact that such detection may not be strictly necessary in realistic FL settings. This mechanism further underscores the feasibility of defending against these attacks with minimal overhead, offering a deployable safeguard for privacy-conscious federated learning systems.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2506.20651 — 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 2026-11-03T07:19:48.862Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).