ResearchTasksJailbreaking Attack DetectionJailbreaking Attack DetectionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedWildJailbreakReGA36Accuracy (MCA)6Apr 21, 2026Role-Playing Jailbreaking PromptsReGA71AccMCA6Apr 21, 2026Misspellings Jailbreaking PromptsReGA68Acc MCA6Apr 21, 2026Technical Terms Jailbreaking PromptsReGA59Accuracy (MCA)6Apr 21, 2026