SemLRA: Lightweight Robust Aggregation Against Poisoning Attacks in Semantic Federated Learning
Semantic federated learning couples task-oriented semantic communication with distributed training, reducing on-device training burden and end-to-end inference latency. However, poisoning through local data, task labels, or transmitted semantic features can degrade task performance and system reliability. We propose se...
Zepei Liu, Zhigang Jin, Zimeng Li et al.
· Electronics · 0 citations