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, poses significant security risks. While prior work has primarily focused on prompt injection attacks, these approaches often require resource-intensive prompt engineering and overlook other critical components, such as chat templates. This paper in