Depth Gives a False Sense of Privacy: LLM Internal States Inversion
No ratings
Presented at USENIX Security 2025 by
Large Language Models (LLMs) are increasingly integrated into daily routines, yet they raise significant privacy and safety concerns. Recent research proposes collaborative inference, which outsources the early-layer inference to ensure data locality, and introduces model safety auditing based on inner neuron patterns. Both techniques expose the LLM's