{"ID":2866018,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.01261","arxiv_id":"2510.01261","title":"Adaptive Federated Learning Defences via Trust-Aware Deep Q-Networks","abstract":"Federated learning is vulnerable to poisoning and backdoor attacks under partial observability. We formulate defence as a partially observable sequential decision problem and introduce a trust-aware Deep Q-Network that integrates multi-signal evidence into client trust updates while optimizing a long-horizon robustness--accuracy objective. On CIFAR-10, we (i) establish a baseline showing steadily improving accuracy, (ii) show through a Dirichlet sweep that increased client overlap consistently improves accuracy and reduces ASR with stable detection, and (iii) demonstrate in a signal-budget study that accuracy remains steady while ASR increases and ROC-AUC declines as observability is reduced, which highlights that sequential belief updates mitigate weaker signals. Finally, a comparison with random, linear-Q, and policy gradient controllers confirms that DQN achieves the best robustness--accuracy trade-off.","short_abstract":"Federated learning is vulnerable to poisoning and backdoor attacks under partial observability. We formulate defence as a partially observable sequential decision problem and introduce a trust-aware Deep Q-Network that integrates multi-signal evidence into client trust updates while optimizing a long-horizon robustness...","url_abs":"https://arxiv.org/abs/2510.01261","url_pdf":"https://arxiv.org/pdf/2510.01261v1","authors":"[\"Vedant Palit\"]","published":"2025-09-25T13:30:09Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.CR\"]","methods":"[]","has_code":false}