Page 159 - 《软件学报》2021年第6期

软件学报 ISSN 1000-9825, CODEN RUXUEW E-mail: jos@iscas.ac.cn
Journal of Software,2021,32(6):1733−1747 [doi: 10.13328/j.cnki.jos.006247] http://www.jos.org.cn
©中国科学院软件研究所版权所有. Tel: +86-10-62562563

∗
个体交互行为的平滑干预模型

1
1,2
1
刘 霄 , 章昭辉 , 魏子明 , 王鹏伟 1
1
(东华大学 计算机科学与技术学院,上海 201620)
2 (上海网络信息服务工程技术研究中心,上海 201804)
通讯作者: 章昭辉, E-mail: zhzhang@dhu.edu.cn

摘 要: 基于交互行为的用户特征提取和身份认证方法是一种重要的身份识别方式,但高频用户的交互行为模式
和操作习惯相对稳定,易被欺诈者模仿,使得现有模型对此类欺诈行为的误判较高.如何使得用户行为主动平滑变化
且可区分,成为解决上述问题的关键.针对此问题,提出一种基于个体交互行为系统平滑干预模型:首先,根据用户历
史交互行为日志从多个维度得到用户的交互行为变化趋势;然后,结合行为的稳定性和偏向性提出行为时域漂移算
法(TDDA),为每个用户确定行为引导的时机;最后,基于 Petri 网提出交互行为重构系统干预模型,在系统中的非关键
路径叠加行为触发因素,引导用户产生新的交互行为习惯.实验证明了提出的方法能够很好地引导用户行为平滑变
化,且产生足够的区分性,使得行为伪装异常检测场景下模型的准确性显著提高.
关键词: 行为干预;交互行为;身份伪装;身份识别;Petri 网建模
中图法分类号: TP309

中文引用格式: 刘霄,章昭辉,魏子明,王鹏伟.个体交互行为的平滑干预模型.软件学报,2021,32(6):1733−1747. http://www.jos.
org.cn/1000-9825/6247.htm
英文引用格式: Liu X, Zhang ZH, Wei ZM, Wang PW. Smooth intervention model of individual interaction behavior. Ruan Jian
Xue Bao/Journal of Software, 2021,32(6):1733−1747 (in Chinese). http://www.jos.org.cn/1000-9825/6247.htm

Smooth Intervention Model of Individual Interaction Behavior
1,2
1
1
LIU Xiao , ZHANG Zhao-Hui , WEI Zi-Ming , WANG Peng-Wei 1
1 (School of Computer Science and Technology, Donghua University, Shanghai 201620, China)
2 (Shanghai Engineering Research Center of Network Information Services, Shanghai 201804, China)
Abstract: User feature extraction and identity authentication methods based on interactive behavior are an important method of identity
recognition. However, for high-frequency users, the interactive behavior patterns and operating habits are relatively stable, which are
easily imitated by fraudsters and making the existing models have a higher misjudgment. The key point to solve the above problems is to
make the user's behavior change smoothly and distinguishably. This study proposes a smooth intervention model based on an individual
interactive behavior system to handle it. Firstly, according to the user history web behavior log, the change trend of user interaction
behavior is obtained from multiple dimensions. Then, combined with the stability and deviation of the behavior, the time-domain drift
algorithm (TDDA) is proposed to determine the behavior guidance time of each user. Finally, an intervention model for interactive
behavior reconstruction systems is proposed, which superimposes behavior trigger factors on non-critical paths in the system to guide
users generating new interactive behavior habits. Experiments prove that the method proposed in this study could guide the user’s

∗ 基金项目: 上海市自然科学基金(19ZR1401900); 上海市科技创新行动计划(19511101302); 国家自然科学基金(61472004,
61602109)
Foundation item: Natural Science Foundation of Shanghai (19ZR1401900); Shanghai Science and Technology Innovation Action
Plan High-Tech Field Project (19511101302); National Natural Science Foundation of China (61472004, 61602109)
本文由“形式化方法与应用”专题特约编辑田聪教授推荐.
收稿时间: 2020-08-30; 修改时间: 2020-10-26; 采用时间: 2020-12-19; jos 在线出版时间: 2021-02-07