Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Attack Detection on InjecAgent Agentic Attacks
Loading...
0.99
Detection Rate
LogReg (Ours)
0.184
0.39325
0.6025
0.81175
Feb 15, 2026
Detection Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Detection Rate
LogReg (Ours)
input=raw activations,...
2026.02
0.99
Llama-as-Judge
acronym=LJ, prompting=...
2026.02
0.215
Feedback
Search any
task
Search any
task
