一作ACL 2026Poster· Natural Language Processing
When Efficiency Meets Safety: A Benchmark Security Analysis of KV Cache Compression in Large Language Models
Xiaoxiao Ma · Kuofeng Gao · Zeyi Lu · Wenxi Jiang · Hao Fang · Hao Wu · Bin Chen · Shu-Tao Xia
摘要
Key-Value (KV) caching is widely used in large language models (LLMs) to enable long-context inference efficiently, yet its security implications remain underexplored. We present the first systematic study of how KV cache compression interacts with jailbreak attacks, evaluating four model familie...