Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

ActorAttack

Benchmarks

Task NameDataset NameSOTA ResultTrend
Safety EvaluationActorAttack
ASR3.5
8
Jailbreak AttackActorAttack (test)
ASR54
4
Adversarial RobustnessActorAttack (out-of-domain)
ASR0.435
4
Showing 3 of 3 rows