基于图卷积网络的社交网络Spammer检测技术
|
摘要
在社交网络中,Spammer未经接收者允许,大量地发送对接收者无用的广告信息,严重地威胁正常用户的信息安全与社交网站的信用体系。针对现有社交网络Spammer检测方法的提取浅层特征与计算复杂度高的问题,提出了一种基于图卷积网络(GCN)的社交网络Spammer检测技术。该方法基于网络结构信息,通过引入网络表示学习算法提取网络局部结构特征,结合重正则化技术条件下的GCN算法获取网络全局结构特征去检测Spammer。在Tagged.com社交网络数据上进行了实验,结果表明,所提方法具有较高的准确率与效率。
In social networks, Spammer send advertisements that are useless to recipients without the recipient's permission, seriously threatening the information security of normal users and the credit system of social networking sites. In order to solve problems of extracting the shallow features and high computational complexity for the existing Spammer detection methods of social networks, a Spammer detection technology based on graph convolutional network(GCN) was proposed. Based on the network structure information, the method introduces the network representation learning algorithm to extract the network local structure feature, and combines the GCN algorithm under the re-regularization technology condition to obtain the network global structure feature to achieve the goal of detecting Spammer. Experiments are done on social network data of Tagged.com. The results show that this method has high accuracy and efficiency.
In social networks, Spammer send advertisements that are useless to recipients without the recipient's permission, seriously threatening the information security of normal users and the credit system of social networking sites. In order to solve problems of extracting the shallow features and high computational complexity for the existing Spammer detection methods of social networks, a Spammer detection technology based on graph convolutional network(GCN) was proposed. Based on the network structure information, the method introduces the network representation learning algorithm to extract the network local structure feature, and combines the GCN algorithm under the re-regularization technology condition to obtain the network global structure feature to achieve the goal of detecting Spammer. Experiments are done on social network data of Tagged.com. The results show that this method has high accuracy and efficiency.
引文
[1]MA HUATENG.Normal and reasonable competition is good for business[C]//World Fortune Forum.2017.
[2]HAROLD NGUYEN.2013 state of social media spam.Technical report[R].2013
[3]STRINGHINI G,KRUEGEL C,VIGNA G.Detecting Spammers on social networks[C]//The 26th Annual Computer Security Applications Conference.2010:1-9.
[4]RAYANA S,AKOGLU L.Collective opinion spam detection:bridging review networks and metadata[C]//The 21th ACM Sigkdd International Conference On Knowledge Discovery And Data Mining.2015:985-994.
[5]LIM E P,NGUYEN V A,JINDAL N,et al.Detecting product review Spammers using rating behaviors[C]//The 19th ACM International Conference On Information and Knowledge Management.2010:939-948.
[6]BENEVENUTO F,MAGNO G,RODRIGUES T,et al.Detecting Spammers on twitter[C]//Collaboration,Electronic Messaging,Anti-Abuse And Spam Conference(CEAS 2010).2010:12.
[7]GAO H,HU J,WILSON C,et al.Detecting and characterizing social spam campaigns[C]//The 10th ACM SIGCOMM Conference on Internet Measurement.2010:35-47.
[8]HU X,TANG J,ZHANG Y,et al.Social Spammer detection in microblogging[C]//(IJCAI 2013).2013:2633-2639.
[9]HU X,TANG J,LIU H.Online social Spammer detection[C]//AAAI.2014:59-65.
[10]HU X,TANG J,GAO H,et al.Social Spammer detection with sentiment information[C]//2014 IEEE International Conference on Data Mining(ICDM).2014:180-189.
[11]KIPF T N,WELLING M.Semi-supervised classification with graph convolutional networks[C]//ICLR.2017.
[12]涂存超,杨成,刘知远,等.网络表示学习综述[J].科学通报,1998,43:1681.TU C C,YANG C,LIU Z Y,et al.Network representation learning:an overview[J].Chinese Science Bulletin,1998,43:1681.
[13]CUI P,WANG X,PEI J,et al.A survey on network embedding[J].Social and Information Networks(Cornell University Library),2017.
[14]PEROZZI B,AL-RFOU R,SKIENA S.Deep Walk:online learning of social representations[C]//The 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2014:701-710.
[15]GROVER A,LESKOVEC J.Node2vec:scalable feature learning for networks[C]//The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2016:855-864.
[16]RIBEIRO L F R,SAVERESE P H P,FIGUEIREDO D R.Struc2vec:learning node representations from structural identity[C]//The 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2017:385-394.
[17]TANG J,QU M,WANG M,ET AL.Line:large-scale information network embedding[C]//The 24th International Conference on World Wide Web.2015:1067-1077.
[18]HENAFF M,BRUNA J,LECUN Y.Deep convolutional networks on graph-structured data[J].Computer Science,2015.
[19]HE K,ZHANG X,REN S,ET Al.Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[20]JAIN A,ZAMIR A R,SAVARESE S,et al.Structural-RNN:deep learning on spatio-temporal graphs[C]//IEEE Conference on Computer Vision and Pattern Recognition.2016:5308-5317.
[21]LI Y,TARLOW D,BROCKSCHMIDT M,ET AL.Gated graph sequence neural networks[J].Computer Science,2015.
[22]SHUMAN D I,NARANG S K,FROSSARD P,et al.The emerging field of signal processing on graphs:extending high-dimensional data analysis to networks and other irregular domains[J].IEEESignal Processing Magazine,2013,30(3):83-98.
[23]HAMMOND D K,VANDERGHEYNST P,GRIBONVAL R.Wavelets on graphs via spectral graph theory[J].Applied and Computational Harmonic Analysis,2011,30(2):129-150.
[24]DEFFERRARD M,BRESSON X,VANDERGHEYNST P.Convolutional neural networks on graphs with fast localized spectral filtering[C]//Advances in Neural Information Processing Systems.2016:3844-3852.
[25]CHUNG F R K.Spectral graph theory[C]//CBMS Regional Conference Series in Mathematics.1996.
[2]HAROLD NGUYEN.2013 state of social media spam.Technical report[R].2013
[3]STRINGHINI G,KRUEGEL C,VIGNA G.Detecting Spammers on social networks[C]//The 26th Annual Computer Security Applications Conference.2010:1-9.
[4]RAYANA S,AKOGLU L.Collective opinion spam detection:bridging review networks and metadata[C]//The 21th ACM Sigkdd International Conference On Knowledge Discovery And Data Mining.2015:985-994.
[5]LIM E P,NGUYEN V A,JINDAL N,et al.Detecting product review Spammers using rating behaviors[C]//The 19th ACM International Conference On Information and Knowledge Management.2010:939-948.
[6]BENEVENUTO F,MAGNO G,RODRIGUES T,et al.Detecting Spammers on twitter[C]//Collaboration,Electronic Messaging,Anti-Abuse And Spam Conference(CEAS 2010).2010:12.
[7]GAO H,HU J,WILSON C,et al.Detecting and characterizing social spam campaigns[C]//The 10th ACM SIGCOMM Conference on Internet Measurement.2010:35-47.
[8]HU X,TANG J,ZHANG Y,et al.Social Spammer detection in microblogging[C]//(IJCAI 2013).2013:2633-2639.
[9]HU X,TANG J,LIU H.Online social Spammer detection[C]//AAAI.2014:59-65.
[10]HU X,TANG J,GAO H,et al.Social Spammer detection with sentiment information[C]//2014 IEEE International Conference on Data Mining(ICDM).2014:180-189.
[11]KIPF T N,WELLING M.Semi-supervised classification with graph convolutional networks[C]//ICLR.2017.
[12]涂存超,杨成,刘知远,等.网络表示学习综述[J].科学通报,1998,43:1681.TU C C,YANG C,LIU Z Y,et al.Network representation learning:an overview[J].Chinese Science Bulletin,1998,43:1681.
[13]CUI P,WANG X,PEI J,et al.A survey on network embedding[J].Social and Information Networks(Cornell University Library),2017.
[14]PEROZZI B,AL-RFOU R,SKIENA S.Deep Walk:online learning of social representations[C]//The 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2014:701-710.
[15]GROVER A,LESKOVEC J.Node2vec:scalable feature learning for networks[C]//The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2016:855-864.
[16]RIBEIRO L F R,SAVERESE P H P,FIGUEIREDO D R.Struc2vec:learning node representations from structural identity[C]//The 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2017:385-394.
[17]TANG J,QU M,WANG M,ET AL.Line:large-scale information network embedding[C]//The 24th International Conference on World Wide Web.2015:1067-1077.
[18]HENAFF M,BRUNA J,LECUN Y.Deep convolutional networks on graph-structured data[J].Computer Science,2015.
[19]HE K,ZHANG X,REN S,ET Al.Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[20]JAIN A,ZAMIR A R,SAVARESE S,et al.Structural-RNN:deep learning on spatio-temporal graphs[C]//IEEE Conference on Computer Vision and Pattern Recognition.2016:5308-5317.
[21]LI Y,TARLOW D,BROCKSCHMIDT M,ET AL.Gated graph sequence neural networks[J].Computer Science,2015.
[22]SHUMAN D I,NARANG S K,FROSSARD P,et al.The emerging field of signal processing on graphs:extending high-dimensional data analysis to networks and other irregular domains[J].IEEESignal Processing Magazine,2013,30(3):83-98.
[23]HAMMOND D K,VANDERGHEYNST P,GRIBONVAL R.Wavelets on graphs via spectral graph theory[J].Applied and Computational Harmonic Analysis,2011,30(2):129-150.
[24]DEFFERRARD M,BRESSON X,VANDERGHEYNST P.Convolutional neural networks on graphs with fast localized spectral filtering[C]//Advances in Neural Information Processing Systems.2016:3844-3852.
[25]CHUNG F R K.Spectral graph theory[C]//CBMS Regional Conference Series in Mathematics.1996.