2025/09/03 by Jigang Fan, J Fan, Fan, Jigang +10 · 1 voice · 5 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Advanced Malware Detection Techniques #Artificial Intelligence (cs.AI) #Biomolecules (q-bio.BM) #Cryptography and Security (cs.CR) #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Bioinformatics #Physical Unclonable Functions (PUFs) and Hardware Security #Quantitative Methods (q-bio.QM) #cs.AI #cs.CR #cs.LG #q-bio.BM #q-bio.QM
paper · pdf · doi:10.48550/arxiv.2509.03487
openalex publication_date 2025/09/03 · arxiv published 2025/09/03 · arxiv updated 2025/10/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.