站内快照 · 国内可打开。外网原文可能无法访问。
- 论文公开站arXiv
Compression Footprints as Security Signals for Model-Poisoning Defense in Federated Learning
Lossy compression is widely used in Federated Learning (FL) but is generally treated as an error source, while conventional poisoning defenses inspect update geometry. In this work, we instead treat the compressor's response as a security signal: the input-dependent distortion an