Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Datasets
MaliciousAgentSkillsBench
Loading...
Benchmarks
Task Name
Dataset Name
Task Name
Dataset Name
SOTA Result
Trend
Results
Malicious skill detection
MaliciousAgentSkillsBench (404 malicious, 502 benign)
Recall
100
9
Malicious Instruction Detection
MaliciousAgentSkillsBench traditional IPI baselines
Precision
63.93
4
Showing 2 of 2 rows
25 / page
50 / page
100 / page
1
Feedback
Search any
task
Search any
task