AI RESEARCH
Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs
arXiv CS.AI
•
ArXi:2603.23269v1 Announce Type: cross Large Language Models(LLMs) are widely deployed, yet are vulnerable to jailbreak prompts that elicit policy-violating outputs. Although prior studies have uncovered these risks, they typically treat all tokens as equally important during prompt mutation, overlooking the varying contributions of individual tokens to triggering model refusals. Consequently, these attacks