ResearchDatasetsAdversarial Jailbreak AttacksFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsJailbreak DefenseAdversarial Jailbreak Attacks Cipher, Instructional Constraint, Prefix Injection, Psychological Coercion (Alternative)100Safety Score (Cipher)5
Jailbreak DefenseAdversarial Jailbreak Attacks Cipher, Instructional Constraint, Prefix Injection, Psychological Coercion (Alternative)100Safety Score (Cipher)5