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

09/01/2020
by   Houxiang Fan, et al.
4

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/14/2022

Link-Backdoor: Backdoor Attack on Link Prediction via Node Injection

Link prediction, inferring the undiscovered or potential links of the gr...
research
09/05/2023

Black-Box Attacks against Signed Graph Analysis via Balance Poisoning

Signed graphs are well-suited for modeling social networks as they captu...
research
10/08/2021

Dyn-Backdoor: Backdoor Attack on Dynamic Link Prediction

Dynamic link prediction (DLP) makes graph prediction based on historical...
research
10/30/2018

Data Poisoning Attack against Unsupervised Node Embedding Methods

Unsupervised node embedding methods (e.g., DeepWalk, LINE, and node2vec)...
research
10/25/2022

Motif-Backdoor: Rethinking the Backdoor Attack on Graph Neural Networks via Motifs

Graph neural network (GNN) with a powerful representation capability has...
research
05/04/2023

Single Node Injection Label Specificity Attack on Graph Neural Networks via Reinforcement Learning

Graph neural networks (GNNs) have achieved remarkable success in various...
research
09/16/2022

Model Inversion Attacks against Graph Neural Networks

Many data mining tasks rely on graphs to model relational structures amo...

Please sign up or login with your details

Forgot password? Click here to reset