SOURCE-LINKED INTELLIGENCE

Characterizing Contention-Induced Reliability Collapse in KV-Cache Timing Side Channels for Multi-Tenant LLM Serving

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Shared key--value (KV) cache reuse improves large language model (LLM) serving, but it can also create a timing side channel that reveals whether a prefix is already cached. Previous work shows that such attacks are possible, but their reliability under realistic multi-tenant contention is less understood. We study this problem through seven experiments on live shared LLM-serving systems. On a vLLM server running DeepSeek-R1-Distill-Llama-8B on NVIDIA GB10, mean Cohen's d drops from 0.7789 with no synthetic workers to 0.2109 with two workers (t=8.412), while higher worker counts cause no stati

Read original source ↗ Open in workspace

recordType

paper

region

Global