ResearchTasksLLM Jailbreaking AttackFor AI assistantsMarkdownContent indexLLM Jailbreaking AttackFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAdvBench (100 samples)Semantic Representation Attack100Attack Success Rate12May 12, 2026