ResearchTasksPhishing and Malicious Prompt ClassificationFor AI assistantsMarkdownContent indexPhishing and Malicious Prompt ClassificationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedProposed Phishing and Malicious Prompt Dataset 21000Proposed Method96Accuracy1Apr 2, 2026