MGA: Momentum Gradient Attack on Network

The adversarial attack methods based on gradient information can adequately find the perturbations, that is, the combinations of rewired links, thereby reducing the effectiveness of the deep learning model-based graph embedding algorithms, but it is also easy to fall into a local optimum. Therefore, this article proposes a momentum gradient attack (MGA) against the graph convolutional network (GCN) model, which can achieve more aggressive attacks with fewer rewiring links. Compared with directly updating the original network using gradient information, integrating the momentum term into the iterative process can stabilize the updating direction, which makes the model jump out of poor local optimum and enhances the method with stronger transferability. Experiments on node classification and community detection methods based on three well-known network embedding algorithms show that MGA has a better attack effect and transferability.

[1]  Alex Bavelas.  A Mathematical Model for Group Structures , 1948 .

[2]  A. Shimbel.  Structural parameters of communication networks , 1953 .

[3]  Boris Polyak.  Some methods of speeding up the convergence of iteration methods , 1964 .

[4]  L. Freeman.  Centrality in social networks conceptual clarification , 1978 .

[5]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[6]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[7]  Yoshua Bengio,et al.  Pattern Recognition and Neural Networks , 1995 .

[8]  D. Lusseau,et al.  The bottlenose dolphin community of Doubtful Sound features a large proportion of long-lasting associations , 2003, Behavioral Ecology and Sociobiology.

[9]  Andrew McCallum,et al.  Automating the Construction of Internet Portals with Machine Learning , 2000, Information Retrieval.

[10]  M E J Newman,et al.  Fast algorithm for detecting community structure in networks. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[11]  M E J Newman,et al.  Finding and evaluating community structure in networks. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[12]  Lada A. Adamic,et al.  The political blogosphere and the 2004 U.S. election: divided they blog , 2005, LinkKDD '05.

[13]  Stephen P. Borgatti,et al.  Centrality and network flow , 2005, Soc. Networks.

[14]  M E J Newman,et al.  Modularity and community structure in networks. , 2006, Proceedings of the National Academy of Sciences of the United States of America.

[15]  Réka Albert,et al.  Near linear time algorithm to detect community structures in large-scale networks. , 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.

[16]  Lise Getoor,et al.  Preserving the Privacy of Sensitive Relationships in Graph Data , 2007, PinKDD.

[17]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[18]  Jean-Loup Guillaume,et al.  Fast unfolding of communities in large networks , 2008, 0803.0476.

[19]  Yizhou Sun,et al.  Graph-based Consensus Maximization among Multiple Supervised and Unsupervised Models , 2009, NIPS.

[20]  John Skvoretz,et al.  Node centrality in weighted networks: Generalizing degree and shortest paths , 2010, Soc. Networks.

[21]  Shishir Nagaraja,et al.  The Impact of Unlinkability on Adversarial Community Detection: Effects and Countermeasures , 2010, Privacy Enhancing Technologies.

[22]  Philip S. Yu,et al.  Limiting link disclosure in social network analysis through subgraph-wise perturbation , 2012, EDBT '12.

[23]  Ke Wang,et al.  Neighborhood randomization for link privacy in social network analysis , 2013, World Wide Web.

[24]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[25]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[26]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[27]  Warih Maharani,et al.  Degree Centrality for Social Network with Opsahl Method , 2015 .

[28]  Mark E. J. Newman,et al.  Community detection in networks: Modularity optimization and maximum likelihood are equivalent , 2016, ArXiv.

[29]  Le Song,et al.  Discriminative Embeddings of Latent Variable Models for Structured Data , 2016, ICML.

[30]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[31]  Seyed-Mohsen Moosavi-Dezfooli,et al.  DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[33]  M. Newman.  Community detection in networks: Modularity optimization and maximum likelihood are equivalent , 2016, Physical review. E.

[34]  Dan Boneh,et al.  The Space of Transferable Adversarial Examples , 2017, ArXiv.

[35]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[36]  Wei Chen,et al.  Interplay between Social Influence and Network Centrality: A Comparative Study on Shapley Centrality and Single-Node-Influence Centrality , 2016, WWW.

[37]  Maria Cláudia Reis Cavalcanti,et al.  Automatic feature selection for supervised learning in link prediction applications: a comparative study , 2017, Knowledge and Information Systems.

[38]  Talal Rahwan,et al.  Hiding individuals and communities in a social network , 2016, Nature Human Behaviour.

[39]  Cheng Ding,et al.  TeamGen: An Interactive Team Formation System Based on Professional Social Network , 2017, WWW.

[40]  Huan Liu,et al.  Toward online node classification on streaming networks , 2017, Data Mining and Knowledge Discovery.

[41]  Sucheta Soundarajan,et al.  The k-peak Decomposition: Mapping the Global Structure of Graphs , 2017, WWW.

[42]  Alex A. Gorodetsky,et al.  Gradient-based optimization for regression in the functional tensor-train format , 2018, J. Comput. Phys..

[43]  Qi Xuan,et al.  Link Weight Prediction Using Supervised Learning Methods and Its Application to Yelp Layered Network , 2018, IEEE Transactions on Knowledge and Data Engineering.

[44]  Stephan Günnemann,et al.  Adversarial Attacks on Node Embeddings , 2018, ICML 2019.

[45]  Qi Xuan,et al.  Fast Gradient Attack on Network Embedding , 2018, ArXiv.

[46]  Yao Zhang,et al.  Energy–entropy competition and the effectiveness of stochastic gradient descent in machine learning , 2018, Molecular Physics.

[47]  Qi Xuan,et al.  Social Synchrony on Complex Networks , 2018, IEEE Transactions on Cybernetics.

[48]  Stephan Günnemann,et al.  Adversarial Attacks on Neural Networks for Graph Data , 2018, KDD.

[49]  Sankaran Mahadevan,et al.  A Bio-Inspired Approach to Traffic Network Equilibrium Assignment Problem , 2018, IEEE Transactions on Cybernetics.

[50]  Le Song,et al.  Adversarial Attack on Graph Structured Data , 2018, ICML.

[51]  Jun Zhu,et al.  Boosting Adversarial Attacks with Momentum , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[52]  Yi-Chang Chiu,et al.  A Network Partitioning Algorithmic Approach for Macroscopic Fundamental Diagram-Based Hierarchical Traffic Network Management , 2018, IEEE Transactions on Intelligent Transportation Systems.

[53]  Dawn Xiaodong Song,et al.  Curriculum Adversarial Training , 2018, IJCAI.

[54]  Jia Liu,et al.  Poisoning Attacks to Graph-Based Recommender Systems , 2018, ACSAC.

[55]  Ajmal Mian,et al.  Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey , 2018, IEEE Access.

[56]  Jascha Sohl-Dickstein,et al.  Adversarial Examples that Fool both Computer Vision and Time-Limited Humans , 2018, NeurIPS.

[57]  Zheng Wang,et al.  Active learning for node classification in assortative and disassortative networks , 2011, KDD.

[58]  Jascha Sohl-Dickstein,et al.  Adversarial Examples that Fool both Human and Computer Vision , 2018, ArXiv.

[59]  Valeria Fionda,et al.  Community Deception or: How to Stop Fearing Community Detection Algorithms , 2018, IEEE Transactions on Knowledge and Data Engineering.

[60]  Minyi Guo,et al.  GraphGAN: Graph Representation Learning with Generative Adversarial Nets , 2017, AAAI.

[61]  Qi Xuan,et al.  GA-Based Q-Attack on Community Detection , 2018, IEEE Transactions on Computational Social Systems.

[62]  Stephan Günnemann,et al.  Adversarial Attacks on Node Embeddings via Graph Poisoning , 2018, ICML.

[63]  Things You May Not Know About Adversarial Example: A Black-box Adversarial Image Attack , 2019, ArXiv.

[64]  MengChu Zhou,et al.  A Novel Method for Detecting New Overlapping Community in Complex Evolving Networks , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[65]  Xin Wang,et al.  An integrated genomic regulatory network of virulence-related transcriptional factors in Pseudomonas aeruginosa , 2019, Nature Communications.

[66]  Boudewijn P F Lelieveldt,et al.  An Efficient Preconditioner for Stochastic Gradient Descent Optimization of Image Registration , 2019, IEEE Transactions on Medical Imaging.

[67]  Kamila B. Muchowska,et al.  Synthesis and breakdown of universal metabolic precursors promoted by iron , 2019, Nature.

[68]  Jie Tang,et al.  Trust Relationship Prediction in Alibaba E-Commerce Platform , 2020, IEEE Transactions on Knowledge and Data Engineering.

[69]  Dacheng Tao,et al.  Adversarial Examples for Hamming Space Search , 2020, IEEE Transactions on Cybernetics.

[70]  Qi Xuan,et al.  Unsupervised Euclidean Distance Attack on Network Embedding , 2019, 2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC).

[71]  Qi Tian,et al.  Adversarial Training Towards Robust Multimedia Recommender System , 2018, IEEE Transactions on Knowledge and Data Engineering.

[72]  Qi Xuan,et al.  Target Defense Against Link-Prediction-Based Attacks via Evolutionary Perturbations , 2018, IEEE Transactions on Knowledge and Data Engineering.

[73]  Fu Song,et al.  Taking Care of the Discretization Problem: A Comprehensive Study of the Discretization Problem and a Black-Box Adversarial Attack in Discrete Integer Domain , 2019, IEEE Transactions on Dependable and Secure Computing.