SafeProtein: Red-Teaming Framework and Benchmark for Protein Foundation Models
This addresses safety concerns for protein foundation models, which are crucial for biological applications, by providing a benchmark and evaluation protocol, though it is incremental as it applies existing red-teaming concepts to a new domain.
The paper tackled the lack of systematic red-teaming for protein foundation models, introducing SafeProtein, a framework that achieved up to 70% attack success rate on state-of-the-art models like ESM3, revealing potential biological safety risks.
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.