ResearchTasksRobustness to Jailbreak AttacksRobustness to Jailbreak AttacksFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAdaptive attackIPO20Harmful Reasoning Ratio3Mar 4, 2026JBB ParaphrasedIPO16.1Harmful Reasoning Ratio3Mar 4, 2026JailbreakV-28KIPO24.5Harmful Reasoning Ratio3Mar 4, 2026