ResearchDatasetsSleeper AgentFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsPoisoning Defense EvaluationSleeper Agent 7x7 Target-Injected Tasks Poisoned19.8Delta Attack Effectiveness5
Poisoning Defense EvaluationSleeper Agent 7x7 Target-Injected Tasks Poisoned19.8Delta Attack Effectiveness5