基于斯塔克尔伯格博弈的在线社交网络扭曲信息干预算法  

Intervention Algorithm for Distorted Information in Online Social Networks Based on Stackelberg Game

作　　者：袁得嵛[1,2] 陈世聪 高见 王小娟[3] YUAN De-yu;CHEN Shi-cong;GAO Jian;WANG Xiao-juan(Department of Police Information Engineering and Cyber Security,People’s Public Security University of China,Beijing 100038,China;Key Laboratory of Safety Precautions and Risk Assessment,Ministry of Public Security,Beijing 100038,China;School of Electronic and Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China)

机构地区：[1]中国人民公安大学警务信息工程与网络安全学院,北京100038 [2]安全防范与风险评估公安部重点实验室,北京100038 [3]北京邮电大学电子工程学院,北京100876

出　　处：《计算机科学》2021年第3期313-319,共7页Computer Science

基　　金：国家自然科学基金(61771072);中国人民公安大学专项项目(2020JWCX01);警务物联网应用技术公安部重点实验室开放课题。

摘　　要：在新冠肺炎疫情期间,社交媒体以前所未有的速度向全世界传播消息。然而,扭曲信息隐藏在海量社交数据中,对国家安全、社会稳定提出了前所未有的挑战。目前的干预措施大多是建立在对关键节点和关键链路进行控制的基础之上,即删帖和封号,往往效果不佳且容易产生副作用。基于扭曲信息的定义和分析,打破传统思维的限定,在信息蔓延过程中通过发布辟谣信息来干扰扭曲信息的演化过程。借助斯塔克尔伯格博弈理论,文中通过设置奖励来鼓励更多的社交网络用户参与信息对冲过程,从而阻止扭曲信息的爆发效应。基于所提出的斯塔克尔伯格博弈模型,分析了斯塔克尔伯格博弈均衡解的存在性和唯一性,并从理论上推导出斯塔克尔伯格博弈的闭式均衡解,提出了基于最优策略的扭曲信息干预算法。实际网络中的仿真实验表明,相比传统的基于网络结构的免疫策略以及其他基于博弈论的干预算法,所提算法最高可将扭曲信息的传播范围分别降低41%和9%,因此能够有效抑制扭曲信息的传播。During the 2019-nCoV epidemic,social media spread news around the world at an unprecedented rate.Distorted information is hidden in massive social data,which presents unprecedented challenges to national security and social stability.Most of the current intervention strategies are based on the control of key nodes and key links,that is,deleting tweets and blocking accounts,which are often ineffective and prone to side effects.Based on the definition and analysis of distorted information,this paper breaks the limitation of traditional thinking and disturbs the evolution of distorted information by publishing clarifications during the spread of distorted information.With the help of Stackelberg game theory,more users are encouraged to participate in the information hedging process by setting up rewards,thereby hindering the explosive effect of distorted information.Based on the established Stackelberg game,the existence and uniqueness of the equilibrium solution are analyzed,and the closed equilibrium solution and information intervention algorithm is proposed.Simulation experiments in the actual network show that the proposed algorithm reduces the spread of distorted information by up to 41%and 9%compared to the traditional immune strategy based on network structure and other intervention algorithms based on game theory,thus can effectively suppress the spread of distor-ted information.

关 键 词：在线社交网络 扭曲信息 斯塔克尔伯格博弈 信息传播 逆向干预 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]