Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models

Name: Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models
Duration: 15 min
Description: Talk from IEEE Symposium on Security and Privacy 2025.

Yingkai Dong, Xiangtao Meng, Ning Yu, Zheng Li, Shanqing Guo

IEEE Symposium on Security and Privacy 2025 · Day 1 · LLM Security