Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Detection on Reconstructed Embedding Space Jailbreak (100 sampled sentences per label)
Loading...
100
Accuracy
Label Forensics
83.36
87.68
92
96.32
Dec 1, 2025
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Label Forensics
Label=0 (Clean Prompt)
2025.12
100
Label Forensics
Label=Avg.
2025.12
92
Label Forensics
Label=1 (Jailbreak)
2025.12
84
Feedback
Search any
task
Search any
task