基于自适应差异化图卷积的社交网络新增恶意用户检测  

Detection of new malicious users in social networks based on adaptive differential graph convolution

作　　者：吴正昊 曾国荪[1] Wu Zhenghao;Zeng Guosun(Dept.of Computer Science&Technology,Tongji University,Shanghai 201804,China;Embedded System&Service Computing Key Laboratory of Ministry of Education,Shanghai 201804,China)

机构地区：[1]同济大学计算机科学及技术系,上海201804 [2]嵌入式系统与服务计算教育部重点实验室,上海201804

出　　处：《计算机应用研究》2023年第9期2820-2825,共6页Application Research of Computers

基　　金：国家自然科学基金资助项目(62072337);国家重点研发计划资助项目(2019YFB1704100)。

摘　　要：社交网络新增恶意用户检测作为一项分类任务,一直面临着数据样本不足、恶意用户标注稀少的问题。在数据有限的情况下,为了能够精确地检测出恶意用户,提出一种基于自适应差异化图卷积网络的检测方法。该方法通过提取社交网络中的用户特征和社交关系构建社交网络图。构建社交网络图后,计算节点与邻居的相似度,并对邻居进行优先级排序,利用优先级顺序采样关键邻居。关键邻居的特征通过自适应权重的加权平均方式聚合到节点自身,以此更新节点特征。特征更新后的节点通过特征降维和归一化计算得到恶意值,利用恶意值判断用户的恶意性。实验表明该方法和其他方法相比,具有更高的恶意用户查全率和整体查准率,并且能够快速地完成对新增用户的检测,证明了自适应差异化图卷积网络能够有效捕捉到少量样本的关键特征。As a classification task,the detection of new malicious users in social networks has been facing the lack of datasets and labels of malicious users.With limited data,this paper proposed a method based on adaptive differential graph convolution to detect malicious users accurately.By extracting user features and social relationships in the social network,the method constructed the social network graph.After this,it calculated the similarities between node and its neighbors to prioritize the neighbors,and used the priority order to sample key neighbors.The node used adaptive weighted average to aggregate the features of key neighbors to itself,to update its features.After feature updating,by feature dimension reduction and normalization,the node got its malicious value,for malicious detection.The experiment results show that,compared to other methods,the proposed method achieves higher precision and overall accuracy on detection of new malicious users,with a satisfactory speed.Results also demonstrate that adaptive differential graph convolutional networks can effectively capture the key features of a small number of data samples.

关 键 词：社交网络 用户分类 机器学习 图神经网络 恶意用户 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]