SafeProtein: Red-Teaming Framework and Benchmark for Protein Foundation Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914081197260800 |
|---|---|
| author | Fan, Jigang Zhou, Zhenghong Jin, Ruofan Cong, Le Wang, Mengdi Zhang, Zaixi |
| author_facet | Fan, Jigang Zhou, Zhenghong Jin, Ruofan Cong, Le Wang, Mengdi Zhang, Zaixi |
| contents | 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 protein foundation models to the best of our knowledge. SafeProtein combines multimodal prompt engineering and heuristic beam search to systematically design red-teaming methods and conduct tests on protein foundation models. We also curated SafeProtein-Bench, which includes a manually constructed red-teaming benchmark dataset and a comprehensive evaluation protocol. SafeProtein achieved continuous jailbreaks on state-of-the-art protein foundation models (up to 70% attack success rate for ESM3), revealing potential biological safety risks in current protein foundation models and providing insights for the development of robust security protection technologies for frontier models. The codes will be made publicly available at https://github.com/jigang-fan/SafeProtein. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03487 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SafeProtein: Red-Teaming Framework and Benchmark for Protein Foundation Models Fan, Jigang Zhou, Zhenghong Jin, Ruofan Cong, Le Wang, Mengdi Zhang, Zaixi Machine Learning Artificial Intelligence Cryptography and Security Biomolecules Quantitative Methods 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 protein foundation models to the best of our knowledge. SafeProtein combines multimodal prompt engineering and heuristic beam search to systematically design red-teaming methods and conduct tests on protein foundation models. We also curated SafeProtein-Bench, which includes a manually constructed red-teaming benchmark dataset and a comprehensive evaluation protocol. SafeProtein achieved continuous jailbreaks on state-of-the-art protein foundation models (up to 70% attack success rate for ESM3), revealing potential biological safety risks in current protein foundation models and providing insights for the development of robust security protection technologies for frontier models. The codes will be made publicly available at https://github.com/jigang-fan/SafeProtein. |
| title | SafeProtein: Red-Teaming Framework and Benchmark for Protein Foundation Models |
| topic | Machine Learning Artificial Intelligence Cryptography and Security Biomolecules Quantitative Methods |
| url | https://arxiv.org/abs/2509.03487 |