Momentum Gradient-based Untargeted Attack on Hypergraph Neural Networks

TL;DR

This paper introduces MGHGA, a novel untargeted adversarial attack method on Hypergraph Neural Networks that modifies node features using a momentum gradient mechanism, demonstrating improved attack effectiveness on benchmark datasets.

Contribution

The paper presents the first attack model specifically designed for HGNNs, utilizing momentum gradients for feature selection and two feature modification approaches for both discrete and continuous data.

Findings

MGHGA achieves a 2% average performance improvement over baselines.

Extensive experiments validate the effectiveness of MGHGA on five benchmark datasets.

The method successfully attacks node and visual object classification tasks.

Abstract

Hypergraph Neural Networks (HGNNs) have been successfully applied in various hypergraph-related tasks due to their excellent higher-order representation capabilities. Recent works have shown that deep learning models are vulnerable to adversarial attacks. Most studies on graph adversarial attacks have focused on Graph Neural Networks (GNNs), and the study of adversarial attacks on HGNNs remains largely unexplored. In this paper, we try to reduce this gap. We design a new HGNNs attack model for the untargeted attack, namely MGHGA, which focuses on modifying node features. We consider the process of HGNNs training and use a surrogate model to implement the attack before hypergraph modeling. Specifically, MGHGA consists of two parts: feature selection and feature modification. We use a momentum gradient mechanism to choose the attack node features in the feature selection module. In the feature modification module, we use two feature generation approaches (direct modification and sign gradient) to enable MGHGA to be employed on discrete and continuous datasets. We conduct extensive experiments on five benchmark datasets to validate the attack performance of MGHGA in the node and the visual object classification tasks. The results show that MGHGA improves performance by an average of 2% compared to the than the baselines.