Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Attack on AdvBench 150 Harmful Behaviors
Loading...
0
ASR
RA-LLM
-4
23
50
77
Sep 18, 2023
ASR
ASR Reduction
Updated 4d ago
Evaluation Results
Method
Method
Links
ASR
ASR Reduction
RA-LLM
Attack=Adv Strings, Mo...
2023.09
0
84
RA-LLM
Attack Type=TAP, Base...
2023.09
12.7
85.3
RA-LLM
Attack Type=AutoDAN-GP...
2023.09
15.3
84.7
RA-LLM
Attack Type=TAP, Base...
2023.09
16
82
RA-LLM
Attack Type=AutoDAN, B...
2023.09
16.7
82
RA-LLM
Attack Type=AutoDAN-GP...
2023.09
41.3
47.4
RA-LLM
Attack Type=AutoDAN, B...
2023.09
42
48
Original LLM
Attack=Adv Strings, Mo...
2023.09
84
-
Original LLM
Attack Type=AutoDAN-GP...
2023.09
88.7
-
Original LLM
Attack Type=AutoDAN, B...
2023.09
90.7
-
Original LLM
Attack Type=TAP, Base...
2023.09
98
-
Original LLM
Attack Type=TAP, Base...
2023.09
98
-
Original LLM
Attack Type=AutoDAN, B...
2023.09
98.7
-
Original LLM
Attack Type=AutoDAN-GP...
2023.09
100
-
Feedback
Search any
task
Search any
task