ResearchDatasetsBackdoor behaviorsFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsBackdoor DetectionBackdoor behaviors (Jailbreak, Watching, Refusal, Password, Country, Sentiment) zero-shot86.8AUROC (zero-shot)36
Backdoor DetectionBackdoor behaviors (Jailbreak, Watching, Refusal, Password, Country, Sentiment) zero-shot86.8AUROC (zero-shot)36