DeepAI AI Chat
Log In Sign Up

GUAP: Graph Universal Attack Through Adversarial Patching

by   Xiao Zang, et al.
Rutgers University

Graph neural networks (GNNs) are a class of effective deep learning models for node classification tasks; yet their predictive capability may be severely compromised under adversarially designed unnoticeable perturbations to the graph structure and/or node data. Most of the current work on graph adversarial attacks aims at lowering the overall prediction accuracy, but we argue that the resulting abnormal model performance may catch attention easily and invite quick counterattack. Moreover, attacks through modification of existing graph data may be hard to conduct if good security protocols are implemented. In this work, we consider an easier attack harder to be noticed, through adversarially patching the graph with new nodes and edges. The attack is universal: it targets a single node each time and flips its connection to the same set of patch nodes. The attack is unnoticeable: it does not modify the predictions of nodes other than the target. We develop an algorithm, named GUAP, that achieves high attack success rate but meanwhile preserves the prediction accuracy. GUAP is fast to train by employing a sampling strategy. We demonstrate that a 5 sampling in each epoch yields 20x speedup in training, with only a slight degradation in attack performance. Additionally, we show that the adversarial patch trained with the graph convolutional network transfers well to other GNNs, such as the graph attention network.


page 1

page 2

page 3

page 4


A Targeted Universal Attack on Graph Convolutional Network

Graph-structured data exist in numerous applications in real life. As a ...

Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Models

Deep neural networks, while generalize well, are known to be sensitive t...

Adversarial Attack on Hierarchical Graph Pooling Neural Networks

Recent years have witnessed the emergence and development of graph neura...

GANI: Global Attacks on Graph Neural Networks via Imperceptible Node Injections

Graph neural networks (GNNs) have found successful applications in vario...

Scalable Attack on Graph Data by Injecting Vicious Nodes

Recent studies have shown that graph convolution networks (GCNs) are vul...

Towards Secrecy-Aware Attacks Against Trust Prediction in Signed Graphs

Signed graphs are widely used to model the trust relationships among use...

Task and Model Agnostic Adversarial Attack on Graph Neural Networks

Graph neural networks (GNNs) have witnessed significant adoption in the ...