Reinforcement Learning-based Black-Box Evasion Attacks to Link Prediction in Dynamic Graphs

TitleReinforcement Learning-based Black-Box Evasion Attacks to Link Prediction in Dynamic Graphs
Publication TypeConference Paper
Year of Publication2022
AuthorsH Fan, B Wang, P Zhou, A Li, Z Xu, C Fu, H Li, and Y Chen
Conference Name2021 Ieee 23rd International Conference on High Performance Computing and Communications, 7th International Conference on Data Science and Systems, 19th International Conference on Smart City and 7th International Conference on Dependability in Sensor, Cl
Date Published01/2022
Abstract

Link prediction in dynamic graphs (LPDG) is an important research problem that has diverse applications such as online recommendations, studies on disease contagion, organizational studies, etc. Various LPDG methods based on graph embedding and graph neural networks have been recently proposed and achieved state-of-the-art performance. In this paper, we study the vulnerability of LPDG methods and propose the first practical black-box evasion attack under this setting. Specifically, given a trained LPDG model, our attack aims to perturb the graph structure, without knowing to model parameters, model architecture, etc., such that the LPDG model makes as many wrong predicted links as possible. We design our attack based on a stochastic policy-based RL algorithm. Moreover, we evaluate our attack on three real-world graph datasets from different application domains. Experimental results show that our attack is both effective and efficient.

DOI10.1109/HPCC-DSS-SmartCity-DependSys53884.2021.00149