Adversarial and Jailbreaking Attack Detection
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.984AUROC
35
May 6, 2026
0.883AUROC
20
Feb 26, 2026
0.862AUROC
20
Feb 26, 2026
0.889AUROC
20
Feb 26, 2026
0.853AUROC
20
Feb 26, 2026
0.968AUROC
20
Feb 26, 2026