Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Attack Detection on Mixed Attacks 105K sample set
Loading...
77
Detection Rate
LogReg (Ours)
37.272
47.586
57.9
68.214
Feb 15, 2026
Detection Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Detection Rate
LogReg (Ours)
input=raw activations,...
2026.02
77
Llama-as-Judge
acronym=LJ, prompting=...
2026.02
73.8
PromptGuard 2
acronym=PG
2026.02
54.4
LlamaGuard
acronym=LG
2026.02
38.8
Feedback
Search any
task
Search any
task