@misc{harmbench,
  title = {HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal},
  url = {https://arxiv.org/abs/2402.04249v2},
  author = {Mantas Mazeika and Long Phan and Xuwang Yin and Andy Zou and Zifan Wang and Norman Mu and Elham Sakhaee and Nathaniel Li and Steven Basart and Bo Li and David Forsyth and Dan Hendrycks},
  year = {2024},
  date = {2024-02-06},
  version = {arXiv:2402.04249v2},
  note = {arXiv:2402.04249v2}
}

@misc{harmbench-nuwa,
  title = {HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal — NUWA research record},
  url = {https://whitzard.tech/en/nuwa/whitzard-index/work/harmbench/},
  version = {2026-10-29.1},
  organization = {NUWA Frontier AI Safety Lab},
  howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--harmbench.json},
  note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--harmbench.json.}
}