Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Alignment on I2P Violence (explicit prompts)
Loading...
1
ASR
SDID
0.52
3.76
7
10.24
Jul 7, 2026
ASR
Updated 17d ago
Evaluation Results
Method
Method
Links
ASR
SDID
Category=Trigger-Specific
2026.07
1
AEGIS
Category=AEGIS (Ours),...
2026.07
1
AEGIS
Category=AEGIS (Ours),...
2026.07
1
SAFREE
Category=Input-Space
2026.07
2
SafeGuider
Category=Input-Space
2026.07
2
SafeClip
Category=Input-Space
2026.07
3
UCE
Category=Trigger-Specific
2026.07
3
Receler
Category=Trigger-Specific
2026.07
3
SLD-Strong
Category=Trigger-Specific
2026.07
3
CAD
Category=Feature Pruning
2026.07
3
SLD-Medium
Category=Trigger-Specific
2026.07
5
ESD-u
Category=Trigger-Specific
2026.07
8
SLD-Weak
Category=Trigger-Specific
2026.07
9
Diff-QuickFix
Category=Trigger-Specific
2026.07
10
SD 2.1
Category=No Alignment
2026.07
12
SD 1.4
Category=No Alignment
2026.07
13
Feedback
Search any
task
Search any
task