Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Concept Unlearning on Prompt Attacks
Loading...
35.7
ASR (ORIG)
ISPF
-0.388
8.981
18.35
27.719
Jun 1, 2026
ASR (ORIG)
ASR (SIMP)
ASR (CONT)
ASR (NOIS)
ASR (REV)
ASR (FUZZ)
Average ASR
Updated 1mo ago
Evaluation Results
Method
Method
Links
ASR (ORIG)
ASR (SIMP)
ASR (CONT)
ASR (NOIS)
ASR (REV)
ASR (FUZZ)
Average ASR
ISPF
Source-Free=true
2026.06
35.7
28.6
8.6
45.2
28.5
0
24
GA
Source-Free=false
2026.06
8.5
3
4
7
16
0
6.4
GA+KL
Source-Free=false
2026.06
8
3
3.5
7
16.5
0
6.3
SIU
Source-Free=false
2026.06
4.5
2.8
2.3
4.5
10
0
4
SPACE
Source-Free=true
2026.06
4
4
4.5
8
10
0
5.1
NPO
Source-Free=false
2026.06
1
2.5
1
2
3.5
0
1.7
Feedback
Search any
task
Search any
task
