mlsanityData to 14 Oct 2026

Adaptive Federated Learning Defences via Trust-Aware Deep Q-Networks

arXiv 2510.01261 ↗First posted 25 Sep 2025cs.LG cs.CRcited by 1

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 10 of its 17 references that are in the map. First posted on arXiv 25 Sep 2025.

Builds on

10 of 17 references.

References · 10

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  4. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  5. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
  6. 2020Blind Backdoors in Deep Learning Modelscited by 182
  7. 2020A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learningcited by 41
  8. 2024Model Poisoning Attacks to Federated Learning via Multi-Round Consistencycited by 18
  9. 2021Multi-Task Federated Reinforcement Learning with Adversariescited by 13
  10. 2025Integrating Identity-Based Identification against Adaptive Adversaries in Federated Learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Federated Client Selection under Partial Visibility: A POMDP Approach with Spatio-Temporal Attentioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025FLARE: Adaptive Multi-Dimensional Reputation for Robust Client Reliability in Federated Learning
  2. 2025OptiGradTrust: Byzantine-Robust Federated Learning with Multi-Feature Gradient Analysis and Reinforcement Learning-Based Trust Weighting
  3. 2026Secure-CHG: A Comprehensive Framework for Robust and Fair Federated Learning via Hybrid Defense and Contribution-Aware Trust
  4. 2026Agentic Trust Coordination for Federated Learning through Adaptive Thresholding and Autonomous Decision Making in Sustainable and Resilient Industrial Networks
  5. 2026Dynamic Meta-Layer Aggregation for Byzantine-Robust Federated Learning
  6. 2026FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement
  7. 2025TrojanDam: Detection-Free Backdoor Defense in Federated Learning through Proactive Model Robustification utilizing OOD Data
  8. 2026Learning from Unreliable Trajectories: Adversarially-Robust Federated Q-Learning