Adversarial Attack on Community Detection by Hiding Individuals

Abstract

It has been demonstrated that adversarial graphs, i.e., graphs with imperceptible perturbations added, can cause deep graph models to fail on node/graph classification tasks. In this paper, we extend adversarial graphs to the problem of community detection which is much more difficult. We focus on black-box attack and aim to hide targeted individuals from the detection of deep graph community detection models, which has many applications in real-world scenarios, for example, protecting personal privacy in social networks and understanding camouflage patterns in transaction networks. We propose an iterative learning framework that takes turns to update two modules: one working as the constrained graph generator and the other as the surrogate community detection model. We also find that the adversarial graphs generated by our method can be transferred to other learning based community detection models.

In Proceedings of The Web Conference 2020, April 20-24, 2020, Taipei, Taiwan. 11 pages

References in corpus (7)

• Modularity and community structure in networks
• DeepWalk: Online Learning of Social Representations
• Maps of random walks on complex networks reveal community structure
• Link communities reveal multiscale complexity in networks
• Adversarial Attacks on Neural Networks for Graph Data
• Scale-free networks are rare
• Hiding Individuals and Communities in a Social Network

Cited by in corpus (8)

• Adversarial Attack and Defense on Graph Data: A Survey
• Adversarial Attack Framework on Graph Embedding Models with Limited Knowledge
• How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implications
• RobustECD: Enhancement of Network Structure for Robust Community Detection
• Surrogate Representation Learning with Isometric Mapping for Gray-box Graph Adversarial Attacks
• Mask-GVAE: Blind Denoising Graphs via Partition
• Multidomain Evolutionary Optimization on Combinatorial Problems in Complex Networks
• Expander Hierarchies for Normalized Cuts on Graphs