GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

1 code implementation • 19 Sep 2023 • Jiahao Yu, Xingwei Lin, Zheng Yu, Xinyu Xing

Remarkably, GPTFuzz achieves over 90% attack success rates against ChatGPT and Llama-2 models, even with suboptimal initial seed templates.