ResearchTasksMulti-turn attack detectionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedCombined LMSYS, SafeDialBench, Synthetic (held-out)Cum. drift threshold99Detection Accuracy10May 1, 2026
Combined LMSYS, SafeDialBench, Synthetic (held-out)Cum. drift threshold99Detection Accuracy10May 1, 2026