Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Defense on DAN
Loading...
42.9
Drop in ASR
Latent Similarity- Best Layer
-58.084
-31.867
-5.65
20.567
Apr 1, 2026
Drop in ASR
Updated 5d ago
Evaluation Results
Method
Method
Links
Drop in ASR
Latent Similarity- Best Layer
Alignment Strategy=Del...
2026.04
42.9
Latent Similarity- Layer 12
Alignment Strategy=Del...
2026.04
21.9
Random
Alignment Strategy=Del...
2026.04
-2.3
KL
Alignment Strategy=Del...
2026.04
-14.2
Perplexity
Alignment Strategy=Del...
2026.04
-38
Self Certainty
Alignment Strategy=Del...
2026.04
-54.2
Feedback
Search any
task
Search any
task