###
Journal of Software:2021.32(2):406-423

机器学习安全攻击与防御机制研究进展和未来挑战
李欣姣,吴国伟,姚琳,张伟哲,张宾
(大连理工大学 软件学院, 辽宁 大连 116620;辽宁省泛在网络与服务软件重点实验室(大连理工大学), 辽宁 大连 116620;大连理工大学 软件学院, 辽宁 大连 116620;鹏城实验室 网络空间安全中心, 广东 深圳 518055;哈尔滨工业大学 计算机科学与技术学院, 黑龙江 哈尔滨 150001)
Progress and Future Challenges of Security Attacks and Defense Mechanisms in Machine Learning
LI Xin-Jiao,WU Guo-Wei,YAO Lin,ZHANG Wei-Zhe,ZHANG Bin
(School of Software Technology, Dalian University of Technology, Dalian 116620, China;Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province(Dalian University of Technology), Dalian 116620, China;School of Software Technology, Dalian University of Technology, Dalian 116620, China;Cyberspace Security Research Center, Peng Cheng Laboratory, Shenzhen 518055, China;School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China)
Abstract
Chart / table
Reference
Similar Articles
Article :Browse 1787   Download 1356
Received:August 12, 2019    Revised:December 01, 2019
> 中文摘要: 机器学习的应用遍及人工智能的各个领域,但因存储和传输安全问题以及机器学习算法本身的缺陷,机器学习面临多种面向安全和隐私的攻击.基于攻击发生的位置和时序对机器学习中的安全和隐私攻击进行分类,分析和总结了数据投毒攻击、对抗样本攻击、数据窃取攻击和询问攻击等产生的原因和攻击方法,并介绍和分析了现有的安全防御机制.最后,展望了安全机器学习未来的研究挑战和方向.
Abstract:Machine learning applications span all areas of artificial intelligence, but due to storage and transmission security issues and the flaws of machine learning algorithms themselves, machine learning faces a variety of security- and privacy-oriented attacks. This survey classifies the security and privacy attacks based on the location and timing of attacks in machine learning, and analyzes the causes and attack methods of data poisoning attacks, adversary attacks, data stealing attacks, and querying attacks. Furthermore, the existing security defense mechanisms are summarized. Finally, a perspective of future work and challenges in this research area are discussed.
文章编号:     中图分类号:    文献标志码:
基金项目:国家自然科学基金(61872053);中央高校基本科研业务费专项资金(DUT19GJ204);广东省重点领域研发计划(2019B010136001);广东省重点科技计划(LZC0023) 国家自然科学基金(61872053);中央高校基本科研业务费专项资金(DUT19GJ204);广东省重点领域研发计划(2019B010136001);广东省重点科技计划(LZC0023)
Foundation items:National Natural Science Foundation of China (61872053); Fundamental Research Funds for the Central Universities (DUT19GJ204); Key-Area Research and Development Program of Guangdong Province (2019B010136001); Key Science and Technology Program of Guangdong Province (LZC0023)
Reference text:

李欣姣,吴国伟,姚琳,张伟哲,张宾.机器学习安全攻击与防御机制研究进展和未来挑战.软件学报,2021,32(2):406-423

LI Xin-Jiao,WU Guo-Wei,YAO Lin,ZHANG Wei-Zhe,ZHANG Bin.Progress and Future Challenges of Security Attacks and Defense Mechanisms in Machine Learning.Journal of Software,2021,32(2):406-423