Wei, Yanjie

AJF: Adaptive Jailbreak Framework Based on the Comprehension Ability of Black-Box Large Language Models

2025 · ArXiv.org

Recent advancements in adversarial jailbreak attacks have exposed critical vulnerabilities in Large Language Models (LLMs), enabling the circumvention of alignment safeguards through increasingly sophisticated prompt manipulations. Our experiments find that the effectiveness of jailbreak strategies …