机器学习模型可解释性方法、应用与安全研究综述.PDF

计 算 机 研 究 与 发 展 Journal of Computer Research and Development 机器学习模型可解释性方法、应用与安全研究综述 纪守领 1 李进锋 1 杜天宇 1 李博 2 1 （浙江大学网络空间安全研究中心 浙江大学计算机科学与技术学院 杭州 310027 ） 2 （伊利诺伊大学香槟分校计算机科学学院 厄巴纳香槟 61822 ） （lijinfeng0713@ ） A Survey on Techniques, Applications and Security of Machine Learning Interpretability 1 1 1 2 Ji Shouling , Li Jinfeng , Du Tianyu , Li Bo 1 （Institute of Cyberspace Research and College of Computer Science and Technology, Zhejiang University, Hangzhou 310027 ） 2 （Department of Computer Science, University of Illinois at Urbana–Champaign, Urbana-Champaign 61822 ） Abstract While machine learning has achieved great success in various domains, the lack of interpretability has limited its widespread applications in real-world tasks, especially security- critical tasks. To overcome this crucial weakness, intensive research on improving the interpretability of machine learning models has emerged, and a plethora of interpretation methods have been proposed to help end users understand its inner working mechanism. However, the research on model interpretation is still in its infancy, and there are a large amount of scientific issues to be resolved. Furthermore, different researchers have different perspectives on solving the interpretation problem and give different definitions for interpretability, and the proposed interpretation methods also have different emphasis. Till now, the research community still lacks a comprehensive understanding of interpretability as well as a scientific guide for the research on model interpretation. In this survey, we review the explanatory problems in machine learning, and make a systematic summary and scientific classification of the existing research works. At the same time, we discuss the potential