← back to paper

Review history

arxiv: 2608.09225 · 2 revisions

Governing the KV Cache: Preventing Timing Side-Channel Leakage in Multi-Tenant LLM Inference

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 4.0
   143851 ms 14074 in 16922 out 2026-08-15T14:25:45.463718+00:00
2. 2026-08-11 CONDITIONAL MODERATE v1.4.0-daily-deepseek-medium novelty 3.0
   99971 ms 14076 in 10867 out 2026-08-11T21:13:58.833683+00:00