@misc{cve-bench,
  title = {CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities},
  url = {https://arxiv.org/abs/2503.17332},
  author = {Yuxuan Zhu and Antony Kellermann and Dylan Bowman and Philip Li and Akul Gupta and Adarsh Danda and Richard Fang and Conner Jensen and Eric Ihli and Jason Benn and Jet Geronimo and Avi Dhir and Sudhit Rao and Kaicheng Yu and Twm Stone and Daniel Kang},
  year = {2025},
  date = {2025-03-21},
  version = {arXiv:2503.17332v4},
  note = {arXiv:2503.17332v4}
}

@misc{cve-bench-nuwa,
  title = {CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities — NUWA research record},
  url = {https://whitzard.tech/en/nuwa/whitzard-index/work/cve-bench/},
  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--cve-bench.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--cve-bench.json.}
}