AIBearisharXiv – CS AI · 4h ago7/10
🧠
TEMPLATEFUZZ: Fine-Grained Chat Template Fuzzing for Jailbreaking and Red Teaming LLMs
Researchers introduce TEMPLATEFUZZ, a fuzzing framework that systematically exploits vulnerabilities in LLM chat templates—a previously overlooked attack surface. The method achieves 98.2% jailbreak success rates on open-source models and 90% on commercial LLMs, significantly outperforming existing prompt injection techniques while revealing critical security gaps in production AI systems.