2020/09/01 by Houxiang Fan, Binghui Wang, Fan, Houxiang +15 · 1 citation
Computer Science · Social Sciences · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Information and Cyber Security #Machine Learning (cs.LG) #Social and Information Networks (cs.SI) #Terrorism, Counterterrorism, and Political Violence
paper · pdf · doi:10.48550/arxiv.2009.00163
openalex publication_date 2020/09/01 · openalex created_date 2022/11/14 · openalex updated_date 2026/07/28
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. 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.