List your company

ResearchFormerly WizWand

Concept Unlearning Robustness

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

Ring-A-Bell adversarial prompts (K77)

1.05ASR (Threshold 0.3)

10

Mar 20, 2026

Ring-A-Bell adversarial prompts K38

1.05ASR (T=0.3)

10

Mar 20, 2026

Ring-A-Bell adversarial prompts (K16)

71.58ASR (T=0.3)

10

Mar 20, 2026