analiza aiqbench
This research investigates the resilience of federated intrusion detection systems against label-flipping poisoning attacks, demonstrating how adversarial self-compromise can degrade attacker performance while maintaining global model stability. By leveraging a Federated Forest aggregation method rather than standard FedAvg, the study highlights detectable anomalies in per-client accuracy that enable Byzantine client identification without requiring data exfiltration. The work provides critical empirical insights into securing distributed machine learning pipelines against sophisticated poisoning threats in non-IID environments.
BRFID: Toward Byzantine-Robust Federated Intrusion Detection
arXiv:2609.28599v1 Announce Type: cross Abstract: Flipping 60\% of training labels from a single Byzantine client using label-flipping model poisoning self-degrades an attacker's own federated detection accuracy, $99.96\%$ (at no poisoning rate) to $84.33\%$ in a three-client federated IDS. Where the Federated global ensemble maintains stable accuracy across all tested poison rates, without a defense mechanism in place and without coordination between attackers. In this paper, we present empirical results quantifying the impact of label-flipping poisoning attacks on a three-client federated IDS trained on CICIDS2017 with non-IID attack subtype distributions across clients. We demonstrate that the signal of the adversarial self-compromise represents a detectable anomaly for exploitation for Byzantine client identification in the absence of target data exfiltration. We note that the aggregation step uses a Federated Forest (tree concatenation) rather than a parametric FedAvg; the results therefore measure the impact of poisoning on per-client performance under ensemble aggregation, and extension to genuine FedAvg with a parametric classifier is planned for future work.
Abstract:Flipping 60\% of training labels from a single Byzantine client using label-flipping model poisoning self-degrades an attacker's own federated detection accuracy, $99.96\%$ (at no poisoning rate) to $84.33\%$ in a three-client federated IDS. Where the Federated global ensemble maintains stable accuracy across all tested poison rates, without a defense mechanism in place and without coordination between attackers. In this paper, we present empirical results quantifying the impact of label-flipping poisoning attacks on a three-client federated IDS trained on CICIDS2017 with non-IID attack subtype distributions across clients. We demonstrate that the signal of the adversarial self-compromise represents a detectable anomaly for exploitation for Byzantine client identification in the absence of target data exfiltration. We note that the aggregation step uses a Federated Forest (tree concatenation) rather than a parametric FedAvg; the results therefore measure the impact of poisoning on per-client performance under ensemble aggregation, and extension to genuine FedAvg with a parametric classifier is planned for future work.
Cryptography and Security (cs.CR); Machine Learning (cs.LG)
arXiv:2609.28599 [cs.CR]
(or arXiv:2609.28599v1 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2609.28599 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 255 cuvinte
Subiecte conexe
Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interface
arXiv · 5 sept. 2026
PVBRF-ID: Private, Verifiable and Byzantine-Robust Federated Intrusion Detection for Oilfield Enterprise Networks
arXiv · 12 oct. 2026
News
Quantum Computing Report · 7 iun. 2026
Cybersecurity in Edge Computing: A Trust-Aware Federated Hybrid Intrusion Detection Framework
arXiv · 1 oct. 2026