Poison to Detect: Early Client-Side Detection of Targeted Overfitting in Federated Learning
Researchers introduce three client-side detection techniques—label flipping, backdoor trigger injection, and model fingerprinting—to identify targeted overfitting attacks orchestrated by a dishonest aggregator in federated learning. Their methods can detect such attacks within 1-2 training rounds, achieving F1 scores up to 0.7, and allow clients to disengage early. Experiments indicate that detection effectiveness varies with cohort composition and method parameters.
Why it matters: This work offers practical early-warning tools for clients in federated learning, potentially improving the security and trustworthiness of these systems against orchestrator-driven attacks.
Full story at: arXiv Cryptography and Security ↗