Side-Channel Attack Reconstructs Local LLM Output from CPU Cache
A new Microsoft-backed paper shows attackers can reconstruct locally deployed LLM outputs by monitoring CPU cache activity during detokenization, without needing shared memory or CPU offloading.
2026-09-09 ~ 2026-09-10 · 2 related posts
- New side-channel attack reconstructs local LLM outputs from CPU cache traces — chaumian · 2026-09-09
- Microsoft researchers show CPU cache attack that reconstructs local LLM output via the detokenizer — dair_ai · 2026-09-10