No AI summary available for this article.
Why It Matters
Lossy compression is widely used in Federated Learning (FL) but is generally treated as an error source, while conventional poisoning defenses inspect update geometry.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
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 introduce the concept of a \emph{compression footprint}: the low-dimensional collection of reconstruction, directional, sparsity, and payload statistics induced by a lossy compressor. We characterize s...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.40312v1 · Indexed 43 minutes ago