Jiahao Yu

Expert
@sherdencooper

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

597

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

31

PromptFuzz. Python

30

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

18

R2E-Gym. Python

12

GPO. Python

8

AIRS. Python

7

XLLM. Python

6

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

3

Monte-Carlo-method. MATLAB

1
10
Apply