Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Adversarial Attack Diversity Analysis on Mistral-7B
Loading...
0.336
Average Attack Similarity
AIC
0.26736
0.28518
0.303
0.32082
Apr 22, 2026
Average Attack Similarity
Average Query Similarity
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Attack Similarity
Average Query Similarity
AIC
Attack Method=AIC Aggr.
2026.04
0.336
0.237
WildTeaming
Attack Method=WT
2026.04
0.271
0.168
AIC
Attack Method=AIC Subtle
2026.04
0.27
0.152
Feedback
Search any
task
Search any
task