ResearchTasksSafety Filter BypassSafety Filter BypassFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMisbinding PromptAttribute Misbinding Attack44.6NSFW-TC Score1Feb 26, 2026SneakypromptSneakyprompt6.63NSFW-TC Score1Feb 26, 2026MMA DiffusionMMA Diffusion6.2NSFW-TC1Feb 26, 20264chan Prompt4chan Prompt0.6NSFW-TC Score1Feb 26, 2026