Structack: Structure-based Adversarial Attacks on Graph Neural Networks

07/23/2021
by   Hussain Hussain, et al.
0

Recent work has shown that graph neural networks (GNNs) are vulnerable to adversarial attacks on graph data. Common attack approaches are typically informed, i.e. they have access to information about node attributes such as labels and feature vectors. In this work, we study adversarial attacks that are uninformed, where an attacker only has access to the graph structure, but no information about node attributes. Here the attacker aims to exploit structural knowledge and assumptions, which GNN models make about graph data. In particular, literature has shown that structural node centrality and similarity have a strong influence on learning with GNNs. Therefore, we study the impact of centrality and similarity on adversarial attacks on GNNs. We demonstrate that attackers can exploit this information to decrease the performance of GNNs by focusing on injecting links between nodes of low similarity and, surprisingly, low centrality. We show that structure-based uninformed attacks can approach the performance of informed attacks, while being computationally more efficient. With our paper, we present a new attack strategy on GNNs that we refer to as Structack. Structack can successfully manipulate the performance of GNNs with very limited information while operating under tight computational constraints. Our work contributes towards building more robust machine learning approaches on graphs.

READ FULL TEXT
research
06/21/2021

Adversarial Attack on Graph Neural Networks as An Influence Maximization Problem

Graph neural networks (GNNs) have attracted increasing interests. With b...
research
10/23/2022

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

Graph neural networks (GNNs) have found successful applications in vario...
research
03/22/2022

Exploring High-Order Structure for Robust Graph Structure Learning

Recent studies show that Graph Neural Networks (GNNs) are vulnerable to ...
research
09/28/2020

Graph Adversarial Networks: Protecting Information against Adversarial Attacks

We study the problem of protecting information when learning with graph ...
research
10/25/2022

FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification

Recently, a lot of research attention has been devoted to exploring Web ...
research
01/16/2020

Estimating Aggregate Properties In Relational Networks With Unobserved Data

Aggregate network properties such as cluster cohesion and the number of ...
research
10/24/2020

Graph Information Bottleneck

Representation learning of graph-structured data is challenging because ...

Please sign up or login with your details

Forgot password? Click here to reset