Jiahao Yu

GPTFuzz. Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

prompt-injection. Official repo for Customized but Compromised: Assessing Prompt Injection Risks in User-Designed GPTs

PromptFuzz. Python

tricks-in-deeplearning. Using different tricks to improve performance of resetnet. The final accuracy:95.21%

R2E-Gym. Python

GPO. Python

AIRS. Python

XLLM. Python

play-with-LLM-lora. a personal notes about using LLM lora finetuning

Monte-Carlo-method. MATLAB