paperSeptember 2025Unreviewed

SafeProtein: Red-Teaming Framework and Benchmark for Protein Foundation Models

Jigang Fan, Zhenghong Zhou, Ruofan Jin, Le Cong, Mengdi Wang, Zaixi Zhang

arXiv.org

Abstract

Proteins play crucial roles in almost all biological processes. The advancement of deep learning has greatly accelerated the development of protein foundation models, leading to significant successes in protein understanding and design. However, the lack of systematic red-teaming for these models has raised serious concerns about their potential misuse, such as generating proteins with biological safety risks. This paper introduces SafeProtein, the first red-teaming framework designed for protei

Framework mappings

NIST AI Risk Management Framework

MEASUREMeasure

Suggested from the entry's categories.

Cite

@misc{fan2025safeprotein,
  title = {{SafeProtein: Red-Teaming Framework and Benchmark for Protein Foundation Models}},
  author = {Jigang Fan and Zhenghong Zhou and Ruofan Jin and Le Cong and Mengdi Wang and Zaixi Zhang},
  year = {2025},
  month = sep,
  eprint = {2509.03487},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2509.03487},
  url = {https://www.semanticscholar.org/paper/b316f37ef9d48c9aa073245df9e65678b8eca33f}
}