
EH
Ehsan Hallaji, Roozbeh Razavi-Far, Mehrdad Saif
· 1 min read
ResearcharXiv cs.AI
FedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in Federated Learning
arXiv:2502.16396v2 Announce Type: replace-cross
Abstract: Federated learning systems are increasingly threatened by data poisoning attacks, where malicious clients compromise global models by contributing tampered updates. Existing defenses often rely on impractical assumptions, such as access to a central test dataset, or fail to generalize across diverse attack types, particularly those involving multiple malicious clients working collaboratively. To address this, we propose Federated Noise-Induced Activation Analysis (FedNIA), a novel defense framework to identify and exclude adversarial clients without relying on any central test dataset. FedNIA injects random noise inputs to analyze the layerwise activation patterns in client models leveraging an autoencoder that detects abnormal behaviors indicative of data poisoning. FedNIA can defend against diverse attack types, including sample poisoning, label flipping, and backdoors, even in scenarios with multiple attacking nodes. Experimental results on non-iid federated datasets demonstrate its effectiveness and robustness, underscoring its potential as a foundational approach for enhancing the security of federated learning systems.
Original source
This story was published by arXiv cs.AI and written by Ehsan Hallaji, Roozbeh Razavi-Far, Mehrdad Saif. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


