ResearchTasksSpoofing attack traceabilityFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedRTP-LX (test)DualGuard87.04AUC20Feb 26, 2026RealToxicityPrompts (test)DualGuard90.11AUC20Feb 26, 2026