List your company

Jailbreak Attack on Advbench Llama2-70B Guard 100 prompts Original

0ASRNo Attack
-3.821.8547.573.15Feb 24, 2024

Evaluation results

MethodLinks
No AttackLLM Model=Llama2-70B, Attack Version=Original2024.020
GCGLLM Model=Llama2-70B, Attack Version=Original2024.020
GCG + PRPLLM Model=Llama2-70B, Attack Version=PRP-B, Access Threat Model=black-box2024.021
GCG + PRPLLM Model=Llama2-70B, Attack Version=PRP-W, Access Threat Model=white-box2024.022
No AttackLLM Model=Guanaco-13B, Attack Version=Original2024.025
No AttackLLM Model=Vicuna-33B, Attack Version=Original2024.0211
GCGLLM Model=Vicuna-33B, Attack Version=Original2024.0216
GCGLLM Model=Guanaco-13B, Attack Version=Original2024.0221
PAPLLM Model=Guanaco-13B, Attack Version=Original2024.0250
GCG + PRPLLM Model=Vicuna-33B, Attack Version=PRP-B, Access Threat Model=black-box2024.0255
PAPLLM Model=Llama2-70B, Attack Version=Original2024.0256
GCG + PRPLLM Model=Vicuna-33B, Attack Version=PRP-W, Access Threat Model=white-box2024.0259
PAPLLM Model=Vicuna-33B, Attack Version=Original2024.0264
GCG + PRPLLM Model=Guanaco-13B, Attack Version=PRP-B, Access Threat Model=black-box2024.0273
PAP + PRPLLM Model=Llama2-70B, Attack Version=PRP-W, Access Threat Model=white-box2024.0274
PAP + PRPLLM Model=Llama2-70B, Attack Version=PRP-B, Access Threat Model=black-box2024.0274
PAP + PRPLLM Model=Guanaco-13B, Attack Version=PRP-B, Access Threat Model=black-box2024.0280
PAP + PRPLLM Model=Vicuna-33B, Attack Version=PRP-B, Access Threat Model=black-box2024.0286
PAP + PRPLLM Model=Guanaco-13B, Attack Version=PRP-W, Access Threat Model=white-box2024.0288
PAP + PRPLLM Model=Vicuna-33B, Attack Version=PRP-W, Access Threat Model=white-box2024.0292
GCG + PRPLLM Model=Guanaco-13B, Attack Version=PRP-W, Access Threat Model=white-box2024.0295