List your company

Jailbreaking on AdvBench (ASR)

0ASRGPTFuzzer
-4235077Jun 8, 2025

Evaluation results

MethodLinks
GPTFuzzerTarget Model=o1-pro, Attack Method=GPTFuzzer2025.060
GPTFuzzerTarget Model=o3-mini, Attack Method=GPTFuzzer2025.060.2
DeepInceptionTarget Model=o3-mini, Attack Method=DeepInception2025.061
Persuade-ATarget Model=Grok-3-Reasoner, Attack Method=Persuade-A2025.061.4
PastTarget Model=Grok-3-Reasoner, Attack Method=Past2025.062.1
Persuade-LTarget Model=o3-mini, Attack Method=Persuade-L2025.062.4
Persuade-LTarget Model=Grok-3-Reasoner, Attack Method=Persuade-L2025.064.3
Persuade-ATarget Model=o3-mini, Attack Method=Persuade-A2025.064.5
GPTFuzzerTarget Model=Qwen3-8B, Attack Method=GPTFuzzer2025.067.1
Persuade-LTarget Model=Gemini-2.5-pro, Attack Method=Persuade-L2025.068.4
Persuade-ATarget Model=Qwen3-8B, Attack Method=Persuade-A2025.068.5
GPTFuzzerTarget Model=Qwen3-32B, Attack Method=GPTFuzzer2025.0610.1
Persuade-ATarget Model=Gemini-2.5-pro, Attack Method=Persuade-A2025.0611
Persuade-LTarget Model=o1-pro, Attack Method=Persuade-L2025.0611.6
Persuade-ATarget Model=o1-pro, Attack Method=Persuade-A2025.0612.4
Persuade-ATarget Model=Qwen3-32B, Attack Method=Persuade-A2025.0612.8
Persuade-LTarget Model=Qwen3-8B, Attack Method=Persuade-L2025.0615.1
Persuade-ATarget Model=QwQ-32B, Attack Method=Persuade-A2025.0616.7
Persuade-ATarget Model=DeepSeek-R1, Attack Method=Persuade-A2025.0619.6
Persuade-LTarget Model=Qwen3-32B, Attack Method=Persuade-L2025.0619.9
PastTarget Model=o3-mini, Attack Method=Past2025.0621.9
DeepInceptionTarget Model=Gemini-2.5-pro, Attack Method=DeepInception2025.0622.4
GPTFuzzerTarget Model=R1-Distill-Llama-8B, Attack Method=GPTFuzzer2025.0624.7
Persuade-LTarget Model=QwQ-32B, Attack Method=Persuade-L2025.0625.3
GPTFuzzerTarget Model=R1-Distill-Qwen-7B, Attack Method=GPTFuzzer2025.0627.7
Persuade-LTarget Model=DeepSeek-R1, Attack Method=Persuade-L2025.0628.3
GPTFuzzerTarget Model=Gemini-2.5-pro, Attack Method=GPTFuzzer2025.0629.6
DeepInceptionTarget Model=o1-pro, Attack Method=DeepInception2025.0631
DeepInceptionTarget Model=Grok-3-Reasoner, Attack Method=DeepInception2025.0632.1
Persuade-ATarget Model=R1-Distill-Llama-8B, Attack Method=Persuade-A2025.0635.4
Persuade-ATarget Model=R1-Distill-Qwen-7B, Attack Method=Persuade-A2025.0637
GPTFuzzerTarget Model=R1-Distill-Qwen-1.5B, Attack Method=GPTFuzzer2025.0638.4
Persuade-LTarget Model=R1-Distill-Llama-8B, Attack Method=Persuade-L2025.0642.4
Persuade-LTarget Model=R1-Distill-Qwen-7B, Attack Method=Persuade-L2025.0642.8
PastTarget Model=Qwen3-8B, Attack Method=Past2025.0644.3
PastTarget Model=R1-Distill-Qwen-7B, Attack Method=Past2025.0644.9
GPTFuzzerTarget Model=QwQ-32B, Attack Method=GPTFuzzer2025.0648.4
PastTarget Model=o1-pro, Attack Method=Past2025.0649.4
HAUNTATTACKTarget Model=o3-mini, Attack Method=Haunt-Avg2025.0649.7
DeepInceptionTarget Model=Qwen3-32B, Attack Method=DeepInception2025.0654.1
HAUNTATTACKTarget Model=Grok-3-Reasoner, Attack Method=Haunt-Avg2025.0655.3
Persuade-LTarget Model=R1-Distill-Qwen-1.5B, Attack Method=Persuade-L2025.0657.4
HAUNTATTACKTarget Model=R1-Distill-Qwen-1.5B, Attack Method=Haunt-Avg2025.0659.2
PastTarget Model=Qwen3-32B, Attack Method=Past2025.0659.2
DeepInceptionTarget Model=Qwen3-8B, Attack Method=DeepInception2025.0661.3
HAUNTATTACKTarget Model=o1-pro, Attack Method=Haunt-Avg2025.0663.9
Persuade-ATarget Model=R1-Distill-Qwen-1.5B, Attack Method=Persuade-A2025.0664.6
GPTFuzzerTarget Model=DeepSeek-R1, Attack Method=GPTFuzzer2025.0664.7
HAUNTATTACKTarget Model=Gemini-2.5-pro, Attack Method=Haunt-Avg2025.0665.3
HAUNTATTACKTarget Model=o3-mini, Attack Method=Haunt-Best2025.0668.7
HAUNTATTACKTarget Model=Grok-3-Reasoner, Attack Method=Haunt-Best2025.0668.9
HAUNTATTACKTarget Model=R1-Distill-Qwen-7B, Attack Method=Haunt-Avg2025.0672.6
PastTarget Model=Gemini-2.5-pro, Attack Method=Past2025.0673.2
DeepInceptionTarget Model=QwQ-32B, Attack Method=DeepInception2025.0676.8
PastTarget Model=QwQ-32B, Attack Method=Past2025.0677.1
HAUNTATTACKTarget Model=R1-Distill-Llama-8B, Attack Method=Haunt-Avg2025.0677.8
HAUNTATTACKTarget Model=Qwen3-8B, Attack Method=Haunt-Avg2025.0678.5
PastTarget Model=R1-Distill-Llama-8B, Attack Method=Past2025.0679.1
HAUNTATTACKTarget Model=Gemini-2.5-pro, Attack Method=Haunt-Best2025.0679.7
DeepInceptionTarget Model=DeepSeek-R1, Attack Method=DeepInception2025.0681.7
PastTarget Model=R1-Distill-Qwen-1.5B, Attack Method=Past2025.0683.6
HAUNTATTACKTarget Model=o1-pro, Attack Method=Haunt-Best2025.0684.5
HAUNTATTACKTarget Model=Qwen3-32B, Attack Method=Haunt-Avg2025.0684.6
PastTarget Model=DeepSeek-R1, Attack Method=Past2025.0684.9
HAUNTATTACKTarget Model=DeepSeek-R1, Attack Method=Haunt-Avg2025.0686.4
HAUNTATTACKTarget Model=R1-Distill-Qwen-1.5B, Attack Method=Haunt-Best2025.0686.8
HAUNTATTACKTarget Model=QwQ-32B, Attack Method=Haunt-Avg2025.0687.2
HAUNTATTACKTarget Model=R1-Distill-Qwen-7B, Attack Method=Haunt-Best2025.0689.1
DeepInceptionTarget Model=R1-Distill-Qwen-7B, Attack Method=DeepInception2025.0689.8
HAUNTATTACKTarget Model=R1-Distill-Llama-8B, Attack Method=Haunt-Best2025.0690.4
DeepInceptionTarget Model=R1-Distill-Llama-8B, Attack Method=DeepInception2025.0691.6
HAUNTATTACKTarget Model=Qwen3-32B, Attack Method=Haunt-Best2025.0692.3
DeepInceptionTarget Model=R1-Distill-Qwen-1.5B, Attack Method=DeepInception2025.0693.4
GPTFuzzerTarget Model=Grok-3-Reasoner, Attack Method=GPTFuzzer2025.0693.6
HAUNTATTACKTarget Model=DeepSeek-R1, Attack Method=Haunt-Best2025.0694.8
HAUNTATTACKTarget Model=Grok-3-Reasoner, Attack Method=Haunt-Multi2025.0695.6
HAUNTATTACKTarget Model=QwQ-32B, Attack Method=Haunt-Best2025.0695.8
HAUNTATTACKTarget Model=Qwen3-8B, Attack Method=Haunt-Best2025.0696.6
HAUNTATTACKTarget Model=o3-mini, Attack Method=Haunt-Multi2025.0697.1
HAUNTATTACKTarget Model=R1-Distill-Qwen-1.5B, Attack Method=Haunt-Multi2025.0698.5
HAUNTATTACKTarget Model=o1-pro, Attack Method=Haunt-Multi2025.0698.9
HAUNTATTACKTarget Model=Gemini-2.5-pro, Attack Method=Haunt-Multi2025.0699.2
HAUNTATTACKTarget Model=R1-Distill-Qwen-7B, Attack Method=Haunt-Multi2025.0699.4
HAUNTATTACKTarget Model=R1-Distill-Llama-8B, Attack Method=Haunt-Multi2025.0699.7
HAUNTATTACKTarget Model=Qwen3-32B, Attack Method=Haunt-Multi2025.0699.7
HAUNTATTACKTarget Model=Qwen3-8B, Attack Method=Haunt-Multi2025.0699.9
HAUNTATTACKTarget Model=QwQ-32B, Attack Method=Haunt-Multi2025.06100
HAUNTATTACKTarget Model=DeepSeek-R1, Attack Method=Haunt-Multi2025.06100