ResearchTasksEnd-to-End Attack EffectivenessEnd-to-End Attack EffectivenessFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedPoisonedSkills 1,070 adversarial samplesSonnet 4.6919Refusal Count8Apr 6, 2026Skill corpusVulMask58.8ASR2Jun 18, 2026