ResearchTasksPrivacy Violation DetectionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedPKU-SafeRLHFDual-agent87.5Acc9Feb 26, 2026CMPL Insurance Multi-turn (test)NeuroFilter0Rbypass3Feb 26, 2026CMPL Insurance Single-turn (test)NeuroFilter0rbypass3Feb 26, 2026Non-private mechanisms n=5000HS0.175SVT32Feb 26, 2026Non-private mechanisms n=500HS0.095SVT32Feb 26, 2026