计算机科学 ›› 2021, Vol. 48 ›› Issue (3): 313-319.doi: 10.11896/jsjkx.200400079

• 信息安全 • 上一篇    下一篇

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

袁得嵛1,2, 陈世聪1, 高见1,2, 王小娟3   

  1. 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
  • 收稿日期:2020-04-20 修回日期:2020-07-29 出版日期:2021-03-15 发布日期:2021-03-05
  • 通讯作者: 高见(gaojian@ppsuc.edu.cn)
  • 作者简介:yuandeyu@ppsuc.edu.cn
  • 基金资助:
    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

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

YUAN De-yu1,2, CHEN Shi-cong1, GAO Jian1,2, WANG Xiao-juan3   

  1. 1 Department of Police Information Engineering and Cyber Security,People’s Public Security University of China,Beijing 100038,China
    2 Key Laboratory of Safety Precautions and Risk Assessment,Ministry of Public Security,Beijing 100038,China
    3 School of Electronic and Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China
  • Received:2020-04-20 Revised:2020-07-29 Online:2021-03-15 Published:2021-03-05
  • About author:YUAN De-yu,born in 1986,Ph.D,lecturer,Ph.D supervisor.His main research interests include cyber security and complex networks.
    GAO Jian,born in 1982,Ph.D,associate professor.His main research interests include cyber security,malware and botnet.
  • Supported by:
    National Natural Science Foundation of China(61771072),Special Project of People’s Public Security University of China(2020JWCX01) and Open Project of the Key Laboratory of the Police Internet of Things Application Technology (Ministry of Public Security).

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。

关键词: 逆向干预, 扭曲信息, 斯塔克尔伯格博弈, 信息传播, 在线社交网络

Abstract: 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.

Key words: Distorted information, Information dissemination, Online social networks, Reverse intervention, Stackelberg game

中图分类号: 

  • TP309
[1]WANG J K,YU H,WANG X H,et al.Dissemination and control model of public opinion in online social networks based on users’ relative weight[J].Systems Engineering-Theory & Practice,2019,39(6):1565-1579.
[2]ZUO L M,XIA P P,HU K X,et al.Propagation model of public opinion about ICO in social network environment[J].Computer Engineering and Design,2019,40(11):3247-3253.
[3]PENG S,WANG G,ZHOU Y,et al.An Immunization Framework for Social Networks Through Big Data Based Influence Modeling[J].IEEE Transactions on Dependable and Secure Computing,2019,16(6):984-995.
[4]SHANG R H,ZHANG W T,JIAO L C,et al.Dynamic Immunization Node Model for Complex Networks Based on Community Structure and Threshold[J].IEEE Transactions on Cyberne-tics,2020(5):1-14.
[5]XIN Y,GAO C,WANG Z,et al.Discerning influential spreaders in complex networks by accounting the spreading heterogeneity of the nodes[J].IEEE Access,2019,7:92070-92078.
[6]LIU Y,WANG X,KURTHS J.Framework of Evolutionary Algorithm for Investigation of Influential Nodes in Complex Networks[J].IEEE Transactions on Evolutionary Computation,2019,23(6):1049-1063.
[7]YANG Y,WU C X,HE M,et al.Negative Influence Minimization Algorithm for Social Networks[J/OL].Journal of System Simulation.http://kns.cnki.net/kcms/detail/11.3092.V.20120120.1422.002.html.2019.
[8]ZHUKOV D,ZALTCMAN A G,KHVATOVA T Y.Forecasting Changes in States in Social Networks and Sentiment Security Using the Principles of Percolation Theory and Stochastic Dynamics[C]//2019 International Conference on Quality Management,Transport and Information Security,Information Technologies(IT&QM&IS).2019:149-153.
[9]ZHENG J,PAN L.Least Cost Rumor Community Blocking optimization in Social Networks[C]//Third International Confe-rence on Security of Smart Cities,Industrial Control System and Communications (SSIC).2018.
[10]JOHNSON N F,LEAHY R,RESTREPO N J,et al.Hidden resilience and adaptive dynamics of the global online hate ecology[J].Nature,2019,573:261-265.
[11]XIAO Y P,YANG Q F,SANG C Y,et al.Rumor DiffusionModel Based on Representation Learning and Anti-Rumor[J].IEEE Transactions on Network and Service Management,2020(5):1-14.
[12]TONG G M,WU W L,GUO L,et al.An Efficient Randomized Algorithm for Rumor Blocking in Online Social Networks[J].arXiv:1701.02368.
[13]SRIVASTAVA A,KANNAN R,CHELMIS C,et al.RecANt:Network-based Recruitment for Active Fake News Correction[C]//2019 IEEE International Conference on Big Data (Big Data).2019:940-949.
[14]YU Y X,WANG L.An advertising game theory decision-ma-king mechanism for overlapping seeds in geo-social network[J].Journal of Computer Research and Development,2019,56(6):1302-1311.
[15]SHAN F F,LI H,ZHU H.Game theory based forwarding control method for social network[J].Journal on Communications,2018,39(3):172-180.
[16]YAO C,ZHANG Y,ZHANG X,et al.Competitive InfluenceBlocking in Online Social Networks:A Case Study on WeChat
[C]//2018 24th Asia-Pacific Conference on Communications (APCC).2018:251-256.
[17]LU P E,PENG Y H,CHANG C S,et al.Percolation Threshold for Competitive Influence in Random Networks[J/OL].IEEE Transactions on Computational Social Systems.https://arxiv.org/pdf/ 1904.05754.pdf,2020.
[18]LIU Y Z,PAN X Z,FU W.Social Network Rumor Spreading Model Based on Bandwagon Game Between Nodes[J].Compu-ter Engineering,2018,44(10):309-314.
[19]LI Q,WANG Z,WU B,et al.Competition and Cooperation:Dynamical Interplay Diffusion Between Social Topic Multiple Messages in Multiplex Networks[J].IEEE Transactions on Computational Social Systems,2019,6(3):467-478.
[20]KALIGOTLA C,YÜCESAN E,CHICK S E.An agent based model of spread of competing rumors through online interactions on social media[C]//Proceedings of the 2015 Winter Simulation Conference.2015:3985-3996.
[21]HE Z,CAI Z,YU J,et al.Cost-efficient strategies for restraining rumor spreading in mobile social networks[J].IEEE Trans.Veh.Technol.,2017,66(3):2789-2800.
[22]MYERSON R B.Game theory:analysis of conflict[M].Harvard University Press,1997.
[23]WAN P,WANG X,WANG X,et al.Intervening coupling diffusion of competitive information in online social networks[J].IEEE Transactions on Knowledge and Data Engineering.DOI:10.1109/TKDE.2019.2954901.
[1] 畅雅雯, 杨波, 高玥琳, 黄靖云.
基于SEIR的微信公众号信息传播建模与分析
Modeling and Analysis of WeChat Official Account Information Dissemination Based on SEIR
计算机科学, 2022, 49(4): 56-66. https://doi.org/10.11896/jsjkx.210900169
[2] 李家文, 郭炳晖, 杨小博, 郑志明.
基于信息传播的致病基因识别研究
Disease Genes Recognition Based on Information Propagation
计算机科学, 2022, 49(1): 264-270. https://doi.org/10.11896/jsjkx.201100129
[3] 桑春艳, 胥文, 贾朝龙, 文俊浩.
社交网络中基于注意力机制的网络舆情事件演化趋势预测
Prediction of Evolution Trend of Online Public Opinion Events Based on Attention Mechanism in Social Networks
计算机科学, 2021, 48(7): 118-123. https://doi.org/10.11896/jsjkx.200600155
[4] 包峻波, 闫光辉, 李俊成.
结合非完全信息博弈的SIR传播模型
SIR Propagation Model Combing Incomplete Information Game
计算机科学, 2020, 47(6): 230-235. https://doi.org/10.11896/jsjkx.190400164
[5] 孙永樾, 李红燕, 张金波.
RAISE:一种高效的社交网络影响成本最小化算法
RAISE:Efficient Influence Cost Minimizing Algorithm in Social Network
计算机科学, 2019, 46(9): 59-65. https://doi.org/10.11896/j.issn.1002-137X.2019.09.007
[6] 袁得嵛, 高见, 叶萌熙, 王小娟.
基于拓扑扩展的在线社交网络恶意信息源定位算法
Malicious Information Source Locating Algorithm Based on Topological Extension in Online Social Network
计算机科学, 2019, 46(5): 129-134. https://doi.org/10.11896/j.issn.1002-137X.2019.05.020
[7] 黄建一, 李建江, 王铮, 方明哲.
基于上下文相似度矩阵的Single-Pass短文本聚类
Single-Pass Short Text Clustering Based on Context Similarity Matrix
计算机科学, 2019, 46(4): 50-56. https://doi.org/10.11896/j.issn.1002-137X.2019.04.008
[8] 宾晟, 孙更新.
基于多关系社交网络的协同过滤推荐算法
Collaborative Filtering Recommendation Algorithm Based on Multi-relationship Social Network
计算机科学, 2019, 46(12): 56-62. https://doi.org/10.11896/jsjkx.181102189
[9] 胡庆成, 张勇, 邢春晓.
基于有重叠社区划分的社会网络影响最大化方法研究
K-clique Heuristic Algorithm for Influence Maximization in Social Network
计算机科学, 2018, 45(6): 32-35. https://doi.org/10.11896/j.issn.1002-137X.2018.06.005
[10] 冯磊, 冀俊忠, 吴晨生.
一种基于信誉机制的科学文献影响力评价方法
New Method for Ranking Scientific Publications with Creditworthiness Mechanism
计算机科学, 2018, 45(11A): 132-137.
[11] 张林姿, 贾传亮.
基于拓扑路径的网络演化传播机制研究
Study of Propagation Mechanism in Networks Based on Topological Path
计算机科学, 2018, 45(11A): 308-314.
[12] 王振飞,朱静阳,郑志蕴,宋玉.
基于R-C模型的微博社区用户影响力分析
Analysis of Microblog Community Users’ Influence Based on R-C Model
计算机科学, 2017, 44(3): 254-258. https://doi.org/10.11896/j.issn.1002-137X.2017.03.052
[13] 王振飞,张利莹,张行进,李伦.
面向时间感知的微博传播模型研究
Research on Temporal Perception-oriented Microblog Propagation Model
计算机科学, 2017, 44(2): 275-278. https://doi.org/10.11896/j.issn.1002-137X.2017.02.046
[14] 贺超波,杨镇雄,洪少文,汤庸,陈国华,郑凯.
应用随机游走的社交网络用户分类方法
User Classification Method in Online Social Network Using Random Walks
计算机科学, 2015, 42(2): 198-203. https://doi.org/10.11896/j.issn.1002-137X.2015.02.042
[15] 李立耀,孙鲁敬,杨家海.
社交网络研究综述
Research on Online Social Network
计算机科学, 2015, 42(11): 8-21. https://doi.org/10.11896/j.issn.1002-137X.2015.11.002
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!