Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Detection on DrAttack using ASR and PGR
Loading...
3
ASR
SelfDefend (Intent)
2.72
4.61
6.5
8.39
Apr 1, 2026
ASR
PGR
Updated 16d ago
Evaluation Results
Method
Method
Links
ASR
PGR
SelfDefend (Intent)
Latency (Sec.)=2.38, M...
2026.04
3
20
GuardReasoner (Post)
Latency (Sec.)=13.14,...
2026.04
3
92
SelfGrader
Latency (Sec.)=0.78, M...
2026.04
3
17
GradientCuff
Latency (Sec.)=19.26,...
2026.04
4
10
Token Highlighter
Latency (Sec.)=15.20,...
2026.04
6
9
SelfDefend (Direct)
Latency (Sec.)=0.80, M...
2026.04
6
54
WildGuard (Post)
Latency (Sec.)=2.78, M...
2026.04
6
95
WildGuard (Pre)
Latency (Sec.)=2.74, M...
2026.04
8
50
GuardReasoner (Pre)
Latency (Sec.)=11.90,...
2026.04
8
36
Llama Guard (Post)
Latency (Sec.)=0.70, M...
2026.04
9
99
LLama-3-8B-Instruct (No Defense)
Latency (Sec.)=0.86
2026.04
10
-
Perplexity Filter
Latency (Sec.)=0.27, M...
2026.04
10
100
GradSafe
2026.04
10
42
Prompt Guard
Latency (Sec.)=16.87,...
2026.04
10
94
Llama Guard (Pre)
Latency (Sec.)=0.62, M...
2026.04
10
84
Feedback
Search any
task
Search any
task