HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal Paper • 2402.04249 • Published Feb 6, 2024 • 4 • 2
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal Paper • 2402.04249 • Published Feb 6, 2024 • 4 • 2