Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teaming

Item #:

085713-1618

Details

DOI: https://doi.org/10.52202/085713-1618
Author(s): Alex Chouldechova, A. Feder Cooper, Solon Barocas, Abhinav Palia, Dan Vann, Hanna Wallach
Pages: 54040-54065 (26 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 38
Date/Location: Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
Series: Advances in Neural Information Processing Systems 38
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/085713-1618
Author(s): Alex Chouldechova, A. Feder Cooper, Solon Barocas, Abhinav Palia, Dan Vann, Hanna Wallach
Pages: 54040-54065 (26 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 38
Date/Location: Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
Series: Advances in Neural Information Processing Systems 38
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)