ResearchTasksMalicious Query Safety EvaluationMalicious Query Safety EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedJailBenchSSD100Refusal Ratio18Apr 21, 2026AdvBenchSSD100Refusal Rate18Apr 21, 2026