large language models (LLMs)

Your Model Is Leaking: Covert Information Transfer through LLM Residual Streams

A residual-stream covert-channel attack hides sensitive information in LLM intermediate activations, recoverable with a simple linear decoder without retraining or weight modification.

This research describes a residual-stream covert-channel attack that hides sensitive information in LLM intermediate activations, enabling recovery with a simple linear decoder without model retraining or weight modification.

arXiv cs.CR·Sep 23, 12:27 UTC · 3d agoAI safety & security in the wild