TAFL: Trust-Aware Federated Learning for Anomalous Client Detection, Isolation, and Recovery

Summary

TAFL, a Trust-Aware Federated Learning framework, combines Subjective Logic and Multi-Agent Systems to detect anomalous clients, isolate them on probation, and reintegrate them after sustained recovery. The authors report 2–4% higher detection and 20–25% lower convergence latency on MNIST and CIFAR10 at 10–30% anomalous-client ratios, and 94.6–97.1% mean detection on CIFAR10 stress tests, with semantic-backdoor attack success reduced to 2.9%.

Related items

• InfoVGPD-FL: Group-level poisoning detection without trusted datasets for secure aggregationSimilar attack · Elsevier Security Journals
• InfoFedPSA: Adaptive Backdoor Attacks on Federated Large Language Models via Poisoning Sensitive Prompt LayersSimilar attack · IEEE Xplore (Security & AI Journals)
• InfoGHOST: GAN-Harnessed Optimization for Strategic Backdoor Persistence With Future Update Anticipation in Non-IID Federated LearningSimilar attack · IEEE Xplore (Security & AI Journals)
• InfoFederated backdoor attack with aggregated triggers optimized by maximum mean discrepancySimilar attack · OpenAlex (peer-reviewed AI security)
• LowLLM Trojans that Increase Response Lengths and CostSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)