ResearchDatasetsLLMail-InjectFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsPrompt Injection ClassificationLLMail-Inject (test)0.956Accuracy4Jailbreak Success EvaluationLLMail-Inject Scenario 293Tool Calls3