Page 302 - 《软件学报》2021年第5期

软件学报 ISSN 1000-9825, CODEN RUXUEW E-mail: jos@iscas.ac.cn
Journal of Software,2021,32(5):1526−1546 [doi: 10.13328/j.cnki.jos.006204] http://www.jos.org.cn
©中国科学院软件研究所版权所有. Tel: +86-10-62562563

∗
面向智能攻击的行为预测研究

1
1
1
马钰锡 , 张全新 , 谭毓安 , 沈 蒙 2,3
1
(北京理工大学 计算机学院,北京 海淀 100081)
2
(北京理工大学 网络空间安全学院,北京 海淀 100081)
3 (鹏城实验室 网络空间安全研究中心,广东 深圳 518055)
通讯作者: 沈蒙, E-mail: shenmeng@bit.edu.cn

摘 要: 人工智能的迅速发展和广泛应用促进了数字技术的整体跃升.然而,基于人工智能技术的智能攻击也逐
渐成为一种新型的攻击手段,传统的攻击防护方式已经不能满足安全防护的实际需求.通过预测攻击行为的未来步
骤,提前部署针对性的防御措施,可以在智能攻击的对抗中取得先机和优势,有效保护系统安全.首先界定了智能攻
击和行为预测的问题域,对相关研究领域进行了概述;然后梳理了面向智能攻击的行为预测的研究方法,对相关工作
进行分类和详细介绍;之后,分别阐述了不同种类的预测方法的原理机制,并从特征及适应范围等角度对各个种类的
方法做进一步对比和分析;最后,展望了智能攻击行为预测的挑战和未来研究方向.
关键词: 攻击预测;行为预测;智能攻击;攻击行为;人工智能
中图法分类号: TP309

中文引用格式: 马钰锡,张全新,谭毓安,沈蒙.面向智能攻击的行为预测研究.软件学报,2021,32(5):1526−1546. http://www.jos.
org.cn/1000-9825/6204.htm
英文引用格式: Ma YX, Zhang QX, Tan YA, Shen M. Research on behavior-prediction for intelligent attacks. Ruan Jian Xue
Bao/Journal of Software, 2021,32(5):1526−1546 (in Chinese). http://www.jos.org.cn/1000-9825/6204.htm

Research on Behavior-Prediction for Intelligent Attacks
1
1
1
MA Yu-Xi , ZHANG Quan-Xin , TAN Yu-An , SHEN Meng 2,3
1 (School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China)
2 (School of Cyberspace Security, Beijing Institute of Technology, Beijing 100081, China)
3 (Cyberspace Security Research Center, Peng Cheng Laboratory, Shenzhen 518055, China)
Abstract: The rapid development and broad application of artificial intelligence have promoted the overall leap in digital technology.
However, intelligent attacks based on artificial intelligence technology have gradually become a new type of attack method. Traditional
attack protection methods have been far from meeting the requirements of security protection. By predicting the future steps of the attack
behavior and deploying targeted defense measures in advance, the opportunities and advantages can be obtained in the confrontation of
intelligent attacks and system security is effectively protected. This study first defines the problem domain of behavior-prediction and
intelligent attacks and outlines its related research areas. Then it combs the research methods of behavior-prediction for intelligent attacks,
and introduces the classification and related work in detail. After that, the principle and mechanism of different types of prediction
methods are explained, respectively. Each type's methods are further compared, discussed, and analyzed from the perspective of
characteristics and adaptation scope. Finally, the challenges and future directions of intelligent attack behavior-prediction are prospected.

∗ 基金项目 : 国家 自然科学基金 (61876019, 61972039); 北京市自 然科学基金 (4192050); 北京市科 技新星计划 (Z2011
00006820006); 广东省重点领域研发计划(2019B010136001); 之江实验室开放课题(2020AA3AB04)
Foundation item: National Natural Science Foundation of China (61876019, 61972039); Natural Science Foundation of Beijing
Municipality (4192050); Beijing Nova Program of Science and Technology (Z201100006820006); Key Research and Development
Program of Guangdong Province (2019B010136001); Opening Fund of Zhejiang Lab. (2020AA3AB04)
收稿时间: 2020-06-17; 修改时间: 2020-09-16, 2020-10-26; 采用时间: 2020-11-17; jos 在线出版时间: 2020-12-02