AISafetyLab：一個全面的AI安全評估與改進框架

AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement

February 24, 2025

作者: Zhexin Zhang, Leqi Lei, Junxiao Yang, Xijie Huang, Yida Lu, Shiyao Cui, Renmiao Chen, Qinglin Zhang, Xinyuan Wang, Hao Wang, Hao Li, Xianqi Lei, Chengwei Pan, Lei Sha, Hongning Wang, Minlie Huang

cs.AI

摘要

隨著人工智慧模型在各種現實場景中的應用日益廣泛，確保其安全性仍然是一個關鍵但尚未充分探索的挑戰。儘管在評估和提升AI安全性方面已投入大量努力，但缺乏標準化框架和全面工具包的問題，對系統性研究和實際應用構成了重大障礙。為彌補這一缺口，我們推出了AISafetyLab，這是一個整合了代表性攻擊、防禦及評估方法的統一框架與工具包。AISafetyLab具備直觀的介面，使開發者能夠無縫應用多種技術，同時保持程式碼庫的良好結構與可擴展性，以支持未來的技術進步。此外，我們對Vicuna進行了實證研究，分析了不同的攻擊與防禦策略，提供了關於其相對有效性的寶貴見解。為了促進AI安全領域的持續研究與發展，AISafetyLab已公開於https://github.com/thu-coai/AISafetyLab，我們承諾將持續維護並改進該平台。

English

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.