Local LLM inference leaks input and output text to an unprivileged co-resident process through cache access patterns in token embedding and timing of autoregressive decoding.
https://github.com/ intel-analytics/ipex-llm
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
I Know What You Said: Unveiling Hardware Cache Side-Channels in Local Large Language Model Inference
Local LLM inference leaks input and output text to an unprivileged co-resident process through cache access patterns in token embedding and timing of autoregressive decoding.