← Search

Elham Sakhaee

2 accepted papers

2024

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

ICML 2024poster

Automated red teaming holds substantial promise for uncovering and mitigating the risks associated with the malicious use of large language models (LLMs), yet the field lacks a standardized evaluation framework to rigorously assess new methods. To address this issue, we introduce HarmBench, a standa…