28
Mirage: Provable Defense Against LLM KV Cache Timing Side Channels with Topology-Aware Isolation
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 intro…
🅲 hạng C