As AI models are increasingly deployed across diverse real-world scenarios, ensuring their safety remains a critical yet underexplored challenge. While substantial efforts have been made to evaluate and enhance AI safety, the lack of a standardized framework and comprehensive toolkit poses significant obstacles to systematic research and practical adoption. To bridge this gap, we introduce AISafetyLab, a unified framework and toolkit that integrates representative attack, defense, and evaluation methodologies for AI safety. AISafetyLab features an intuitive interface that enables developers to seamlessly apply various techniques while maintaining a well-structured and extensible codebase for future advancements. Additionally, we conduct empirical studies on Vicuna, analyzing different attack and defense strategies to provide valuable insights into their comparative effectiveness. To facilitate ongoing research and development in AI safety, AISafetyLab is publicly available at https://github.com/thu-coai/AISafetyLab, and we are committed to its continuous maintenance and improvement.
@article{arxiv.2502.16776,
title = {AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement},
author = {Zhexin Zhang and Leqi Lei and Junxiao Yang and Xijie Huang and Yida Lu and Shiyao Cui and Renmiao Chen and Qinglin Zhang and Xinyuan Wang and Hao Wang and Hao Li and Xianqi Lei and Chengwei Pan and Lei Sha and Hongning Wang and Minlie Huang},
journal= {arXiv preprint arXiv:2502.16776},
year = {2025}
}