List your company

LLM Safety Defense on MTSA-R3

23.5ASRMTSA-T3
21.4635.234962.77May 22, 2025

Evaluation results

MethodLinks
MTSA-T3Target Model=Zephyr-7B-Beta, Iteration=32025.0523.5
MTSA-T3Target Model=Llama2-7B-Chat, Iteration=32025.0524
MTSA-T2Target Model=Llama2-7B-Chat, Iteration=22025.0527.5
MTSA-T2Target Model=Zephyr-7B-Beta, Iteration=22025.0530.5
MTSA-T1Target Model=Llama2-7B-Chat, Iteration=12025.0532
MART-T3Target Model=Llama2-7B-Chat, Iteration=32025.0536.5
MART-T2Target Model=Llama2-7B-Chat, Iteration=22025.0537.5
HARM-T3Target Model=Llama2-7B-Chat, Iteration=32025.0539
HARM-T2Target Model=Llama2-7B-Chat, Iteration=22025.0541
MART-T1Target Model=Llama2-7B-Chat, Iteration=12025.0541
MTSA-T1Target Model=Zephyr-7B-Beta, Iteration=12025.0542.5
HARM-T1Target Model=Llama2-7B-Chat, Iteration=12025.0543.5
MART-T3Target Model=Zephyr-7B-Beta, Iteration=32025.0548.5
BaselineTarget Model=Llama2-7B-Chat2025.0550.5
MART-T2Target Model=Zephyr-7B-Beta, Iteration=22025.0551
HARM-T3Target Model=Zephyr-7B-Beta, Iteration=32025.0552.5
HARM-T2Target Model=Zephyr-7B-Beta, Iteration=22025.0558.5
MART-T1Target Model=Zephyr-7B-Beta, Iteration=12025.0561.5
HARM-T1Target Model=Zephyr-7B-Beta, Iteration=12025.0565
BaselineTarget Model=Zephyr-7B-Beta2025.0574.5