一作ACL 2026Findings· Findings of ACL
FLASH : Focused Layer Attention Sink Hijacking
Siyuan Deng · Yerong Li · Fanhua Shang · Hongying Liu
摘要
Despite advances in safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreaking attacks. However, prevailing methods suffer from a dichotomy of limitations: they either rely on prohibitive iterative optimization in the input space (leading to high computational costs) or fail...