cs.AI, cs.CR, cs.SE

TEMPLATEFUZZ: Fine-Grained Chat Template Fuzzing for Jailbreaking and Red Teaming LLMs

arXiv:2604.12232v1 Announce Type: cross
Abstract: Large Language Models (LLMs) are increasingly deployed across diverse domains, yet their vulnerability to jailbreak attacks, where adversarial inputs bypass safety mechanisms to elicit harmful outputs,…