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.

通过设计一种新的 HGNNs 攻击模型，即 MGHGA，集中在修改节点特征上，本论文试图填补现有研究中对 HGNNs 敌对攻击的研究空白，通过在特征选择和特征修改模块中使用动量梯度机制和特征生成方法，MGHGA 能够在离散和连续数据集上有效对节点和视觉对象分类任务进行攻击，并在实验证明相对于基准方法，MGHGA 的攻击性能平均提升了 2%。

基于动量梯度的超图神经网络非定向攻击

Momentum Gradient-based Untargeted Attack on Hypergraph Neural Networks

We study black-box attacks on machine learning classifiers where each query
to the model incurs some cost or risk of detection to the adversary. We focus
explicitly on minimizing the number of queries as a major objective.
Specifically, we consider the problem of attacking machine learning classifiers
subject to a budget of feature modification cost while minimizing the number of
queries, where each query returns only a class and confidence score. We
describe an approach that uses Bayesian optimization to minimize the number of
queries, and find that the number of queries can be reduced to approximately
one tenth of the number needed through a random strategy for scenarios where
the feature modification cost budget is low.

本文研究了针对机器学习分类器的黑盒攻击，其中每个向模型的查询都会给对手带来一些代价或检测风险。我们的重点是将查询次数最小化作为主要目标。具体而言，我们考虑了在最小化查询次数的同时遵守特征修改成本预算的机器学习分类器攻击问题。我们描述了一种利用贝叶斯优化来最小化查询次数的方法，并发现，在特征修改成本预算较低的情况下，与随机策略相比，查询次数可以减少到大约原来的十分之一。