RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction

Open Webpage

Tanqiu Jiang, Zian Wang, Jiacheng Liang, Changjiang Li, Yuhui Wang, Ting Wang

Published: 01 Jan 2025, Last Modified: 14 May 2025ICLR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0