Compression Footprints as Security Signals for Model-Poisoning Defense in Federated Learning

Paper recorded by Signals 4 on 2026-09-30 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-30 on arXiv · recorded by Signals 4 on 2026-10-01

Category: cs.LG · 机器学习 · first seen 2026-10-01

Abstract

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 and payload behavior induced by lossy compression can expose differences between honest and attack-generated updates. We i

Read on arXiv →