ResearchTasksLLM security defenseLLM security defenseFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMacro-averaged GPT-4o, Llama-3 8B, and Mistral-7B (test)Layered Security Framework11.3Attack Success Rate (ASR)6Jun 19, 2026
Macro-averaged GPT-4o, Llama-3 8B, and Mistral-7B (test)Layered Security Framework11.3Attack Success Rate (ASR)6Jun 19, 2026