GraphAttacker: A General Multi-Task GraphAttack Framework

01/18/2021
by   Jinyin Chen, et al.
0

Graph Neural Networks (GNNs) have been successfully exploited in graph analysis tasks in many real-world applications. However, GNNs have been shown to have potential security issues imposed by adversarial samples generated by attackers, which achieved great attack performance with almost imperceptible perturbations. What limit the wide application of these attackers are their methods' specificity on a certain graph analysis task, such as node classification or link prediction. We thus propose GraphAttacker, a novel generic graph attack framework that can flexibly adjust the structures and the attack strategies according to the graph analysis tasks. Based on the Generative Adversarial Network (GAN), GraphAttacker generates adversarial samples through alternate training on three key components, the Multi-strategy Attack Generator (MAG), the Similarity Discriminator (SD), and the Attack Discriminator(AD). Furthermore, to achieve attackers within perturbation budget, we propose a novel Similarity Modification Rate (SMR) to quantify the similarity between nodes thus constrain the attack budget. We carry out extensive experiments and the results show that GraphAttacker can achieve state-of-the-art attack performance on graph analysis tasks of node classification, graph classification, and link prediction. Besides, we also analyze the unique characteristics of each task and their specific response in the unified attack framework. We will release GraphAttacker as an open-source simulation platform for future attack researches.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/20/2022

Sparse Vicious Attacks on Graph Neural Networks

Graph Neural Networks (GNNs) have proven to be successful in several pre...
research
12/30/2022

GANExplainer: GAN-based Graph Neural Networks Explainer

With the rapid deployment of graph neural networks (GNNs) based techniqu...
research
09/13/2021

Deep Generative Models to Extend Active Directory Graphs with Honeypot Users

Active Directory (AD) is a crucial element of large organizations, given...
research
10/08/2021

Dyn-Backdoor: Backdoor Attack on Dynamic Link Prediction

Dynamic link prediction (DLP) makes graph prediction based on historical...
research
05/23/2020

Adversarial Attack on Hierarchical Graph Pooling Neural Networks

Recent years have witnessed the emergence and development of graph neura...
research
05/22/2021

A Robust and Generalized Framework for Adversarial Graph Embedding

Graph embedding is essential for graph mining tasks. With the prevalence...
research
02/25/2022

Projective Ranking-based GNN Evasion Attacks

Graph neural networks (GNNs) offer promising learning methods for graph-...

Please sign up or login with your details

Forgot password? Click here to reset