Metraipolis › archive › dc_77bf70e7a600
Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interface — arXiv:2609.03420
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.03420
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T01:11:49.146Z
- SHA-256 of the archived text
d84ba381f5ca75a077ad469238c456a9f9ef521d537330e1e44458a979e3aa46- Stable URL of this page
https://metraipolis.com/documento/dc_77bf70e7a600
How to cite
Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interface — arXiv:2609.03420 — arXiv (en), https://arxiv.org/abs/2609.03420 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_77bf70e7a600 (Metraipolis archive dc_77bf70e7a600, sha256 d84ba381f5ca75a077ad469238c456a9f9ef521d537330e1e44458a979e3aa46)
BibTeX
@misc{dc77bf70e7a600,
title = {Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interface — arXiv:2609.03420},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.03420},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_77bf70e7a600; sha256 d84ba381f5ca75a077ad469238c456a9f9ef521d537330e1e44458a979e3aa46},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03420. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Federated learning enables privacy-conscious collaboration for network intrusion detection without centralizing sensitive traffic data, yet its deployment in operational environments must simultaneously satisfy three competing requirements: formal differential privacy guaranties, tolerance to Byzantine-adversarial participants, and reliable detection coverage across severely imbalanced attack categories. Existing literature treats these properties as independently composable, an assumption that this paper challenges both theoretically and empirically. In this paper, we study how these requirements interact in class-imbalanced federated NIDS and introduce geometric indistinguishability as a conceptual lens for a regime in which privacy-induced dispersion in client updates can make minority-class signals harder for robust aggregation to preserve. Using UNSW-NB15 as a case study, we evaluate DP-SGD combined with coordinate-wise median under label-flip and model-poisoning attacks, with threat coverage assessed across attack categories. Our results provide initial evidence that the joint use of privacy noise and robust aggregation can disproportionately degrade detection of rare attacks relative to majority classes. We also show that part of the observed collapse under strong privacy can arise from training miscalibration, while a residual performance floor may remain for ultra-rare categories even after epsilon-dependent tuning. These findings motivate studying privacy, robustness, and rare-attack coverage jointly rather than as independently composable properties, and suggest that aggregation-aware modeling and sample-aware evaluation are promising directions for trustworthy federated NIDS. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.AI). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.03420 — 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 2026-10-17T00:28:02.953Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).