关键节点双目标优化的虚假信息传播控制模型  

Disinformation spreading control model based on key nodesbi-objective optimization

作　　者：荆军昌 张志勇 班爱莹[1,2] 高东钧 JING Junchang;ZHANG Zhiyong;BAN Aiying;GAO Dongjun(Information Engineering College,Henan University of Science and Technology,Luoyang 471023,China;Henan International Joint Laboratory of Cyberspace Security Applications,Henan University of Science and Technology,Luoyang 471023,China)

机构地区：[1]河南科技大学信息工程学院,河南洛阳471023 [2]河南科技大学河南省网络空间安全应用国际联合实验室,河南洛阳471023

出　　处：《西安电子科技大学学报》2024年第1期201-209,共9页Journal of Xidian University

基　　金：国家自然科学基金(61972133);河南省中原科技创新领军人才项目(204200510021)。

摘　　要：虚假信息传播控制是全球网络空间安全治理的热点领域。针对目前在线社交网络中的虚假信息传播控制研究,尚未考虑对关键节点集控制所产生的成本开销这一实际问题,提出了一种基于关键节点双目标优化的虚假信息传播控制模型。首先,根据用户节点在社交网络1-hop和2-hop区域的传播影响力以及节点的度中心性、k-shell等多种复杂网络特征,对两个优化目标(控制效果和控制成本)进行数学形式化表示;其次,设计一种融合自适应非线性策略的位翻转变异算法,实现对离散搜索空间的第2代非支配排序遗传算法改进,并将改进后第2代非支配排序遗传算法用于虚假信息传播关键节点集的选取,从而实现虚假信息传播控制效果最大化,控制成本开销最小化;最后,通过在真实在线社交网络平台上开展实验,分析模型参数对控制成本和控制效果的影响。实验结果表明,该模型与现有方法相比,在控制成本和控制效果的组合指标R TCTE上具有明显的优势。该模型适用于大规模复杂社交网络下最低成本的虚假信息传播控制。The spread control of disinformation is a hot area of global cyberspace security governance.At present,the research on the spread control of disinformation in online social networks has not considered the actual problem of the cost incurred by the control of key nodes set.This paper proposes a disinformation spreading control model based on key nodes bi-objective optimization.First,according to the spread influence of social user nodes in the 1-hop and 2-hop areas,as well as the degree centrality of nodes,k-shell and other complex network characteristics,the bi-objective including the control effect and control cost is expressed mathematically.Second,a bit flipping mutation algorithm incorporating adaptive nonlinear strategy is designed to improve the performance of the NSGA-Ⅱalgorithm in discrete search space.The improved NSGA-Ⅱalgorithm is used to select a key nodes set of disinformation spreading,which maximizes the effect of disinformation spreading control and minimizes the control cost.Finally,the experiment is carried out on a real online social network platform,with the influence of model parameters on the control cost and control effect analyzed and discussed.Experimental results show that this model has specific and obvious advantages over the existing methods in the combination index R TCTE of control cost and control effect.This model is applicable to the lowest cost disinformation spreading control in large-scale complex social networks.

关 键 词：社交网络 虚假信息 关键节点 遗传算法 第2代非支配排序遗传算法 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]