├── .gitignore ├── LICENSE ├── README.md └── attack-artifacts ├── DSN ├── attack-info.json ├── evaluation.json ├── submission.json └── white_box │ ├── llama-2-7b-chat-hf.json │ └── vicuna-13b-v1.5.json ├── GCG ├── attack-info.json ├── transfer │ ├── gpt-3.5-turbo-1106.json │ └── gpt-4-0125-preview.json └── white_box │ ├── llama-2-7b-chat-hf.json │ └── vicuna-13b-v1.5.json ├── JBC ├── attack-info.json └── manual │ ├── gpt-3.5-turbo-1106.json │ ├── gpt-4-0125-preview.json │ ├── llama-2-7b-chat-hf.json │ └── vicuna-13b-v1.5.json ├── PAIR ├── attack-info.json └── black_box │ ├── gpt-3.5-turbo-1106.json │ ├── gpt-4-0125-preview.json │ ├── llama-2-7b-chat-hf.json │ └── vicuna-13b-v1.5.json ├── prompt_with_random_search ├── attack-info.json └── black_box │ ├── gpt-3.5-turbo-1106.json │ ├── gpt-4-0125-preview.json │ ├── llama-2-7b-chat-hf.json │ └── vicuna-13b-v1.5.json └── test-artifact ├── attack-info.json ├── black_box ├── llama-2-7b-chat-hf.json └── vicuna-13b-v1.5.json └── white_box └── vicuna-13b-v1.5.json /.gitignore: -------------------------------------------------------------------------------- 1 | .DS_Store 2 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/README.md -------------------------------------------------------------------------------- /attack-artifacts/DSN/attack-info.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/DSN/attack-info.json -------------------------------------------------------------------------------- /attack-artifacts/DSN/evaluation.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/DSN/evaluation.json -------------------------------------------------------------------------------- /attack-artifacts/DSN/submission.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/DSN/submission.json -------------------------------------------------------------------------------- /attack-artifacts/DSN/white_box/llama-2-7b-chat-hf.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/DSN/white_box/llama-2-7b-chat-hf.json -------------------------------------------------------------------------------- /attack-artifacts/DSN/white_box/vicuna-13b-v1.5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/DSN/white_box/vicuna-13b-v1.5.json -------------------------------------------------------------------------------- /attack-artifacts/GCG/attack-info.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/GCG/attack-info.json -------------------------------------------------------------------------------- /attack-artifacts/GCG/transfer/gpt-3.5-turbo-1106.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/GCG/transfer/gpt-3.5-turbo-1106.json -------------------------------------------------------------------------------- /attack-artifacts/GCG/transfer/gpt-4-0125-preview.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/GCG/transfer/gpt-4-0125-preview.json -------------------------------------------------------------------------------- /attack-artifacts/GCG/white_box/llama-2-7b-chat-hf.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/GCG/white_box/llama-2-7b-chat-hf.json -------------------------------------------------------------------------------- /attack-artifacts/GCG/white_box/vicuna-13b-v1.5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/GCG/white_box/vicuna-13b-v1.5.json -------------------------------------------------------------------------------- /attack-artifacts/JBC/attack-info.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/JBC/attack-info.json -------------------------------------------------------------------------------- /attack-artifacts/JBC/manual/gpt-3.5-turbo-1106.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/JBC/manual/gpt-3.5-turbo-1106.json -------------------------------------------------------------------------------- /attack-artifacts/JBC/manual/gpt-4-0125-preview.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/JBC/manual/gpt-4-0125-preview.json -------------------------------------------------------------------------------- /attack-artifacts/JBC/manual/llama-2-7b-chat-hf.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/JBC/manual/llama-2-7b-chat-hf.json -------------------------------------------------------------------------------- /attack-artifacts/JBC/manual/vicuna-13b-v1.5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/JBC/manual/vicuna-13b-v1.5.json -------------------------------------------------------------------------------- /attack-artifacts/PAIR/attack-info.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/PAIR/attack-info.json -------------------------------------------------------------------------------- /attack-artifacts/PAIR/black_box/gpt-3.5-turbo-1106.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/PAIR/black_box/gpt-3.5-turbo-1106.json -------------------------------------------------------------------------------- /attack-artifacts/PAIR/black_box/gpt-4-0125-preview.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/PAIR/black_box/gpt-4-0125-preview.json -------------------------------------------------------------------------------- /attack-artifacts/PAIR/black_box/llama-2-7b-chat-hf.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/PAIR/black_box/llama-2-7b-chat-hf.json -------------------------------------------------------------------------------- /attack-artifacts/PAIR/black_box/vicuna-13b-v1.5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/PAIR/black_box/vicuna-13b-v1.5.json -------------------------------------------------------------------------------- /attack-artifacts/prompt_with_random_search/attack-info.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/prompt_with_random_search/attack-info.json -------------------------------------------------------------------------------- /attack-artifacts/prompt_with_random_search/black_box/gpt-3.5-turbo-1106.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/prompt_with_random_search/black_box/gpt-3.5-turbo-1106.json -------------------------------------------------------------------------------- /attack-artifacts/prompt_with_random_search/black_box/gpt-4-0125-preview.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/prompt_with_random_search/black_box/gpt-4-0125-preview.json -------------------------------------------------------------------------------- /attack-artifacts/prompt_with_random_search/black_box/llama-2-7b-chat-hf.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/prompt_with_random_search/black_box/llama-2-7b-chat-hf.json -------------------------------------------------------------------------------- /attack-artifacts/prompt_with_random_search/black_box/vicuna-13b-v1.5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/prompt_with_random_search/black_box/vicuna-13b-v1.5.json -------------------------------------------------------------------------------- /attack-artifacts/test-artifact/attack-info.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/test-artifact/attack-info.json -------------------------------------------------------------------------------- /attack-artifacts/test-artifact/black_box/llama-2-7b-chat-hf.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/test-artifact/black_box/llama-2-7b-chat-hf.json -------------------------------------------------------------------------------- /attack-artifacts/test-artifact/black_box/vicuna-13b-v1.5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/test-artifact/black_box/vicuna-13b-v1.5.json -------------------------------------------------------------------------------- /attack-artifacts/test-artifact/white_box/vicuna-13b-v1.5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JailbreakBench/artifacts/HEAD/attack-artifacts/test-artifact/white_box/vicuna-13b-v1.5.json --------------------------------------------------------------------------------