ResearchTasksJailbreak and Phishing Prompt ClassificationJailbreak and Phishing Prompt ClassificationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updated60 Malicious QueriesXu et al.92Accuracy (Jailbreak/Phishing)1Apr 2, 2026