arXiv:2611.10756v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as shared multi-tenant services, relying on advanced optimizations like KV cache and prefix sharing to improve throughput and reduce latency. However, these optimizations introduce a critical vulnerability: attackers can exploit time-to-first-token (TTFT) variations between KV cache hits and misses to infer sensitive prompt tokens via prefix-matching side-channel attacks.
Mirage: Provable Defense Against LLM KV Cache Timing Side Channels with Topology-Aware Isolation
About this summary. This is a short excerpt from the description that arXiv cs.CR published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2611.10756
Source attribution: headline and facts are from arXiv cs.CR (arxiv.org). Summary method: excerpt of the source description. See our source attribution policy.




