English

HyperAttack: Multi-Gradient-Guided White-box Adversarial Structure Attack of Hypergraph Neural Networks

Machine Learning 2023-02-27 v1 Artificial Intelligence Cryptography and Security

Abstract

Hypergraph neural networks (HGNN) have shown superior performance in various deep learning tasks, leveraging the high-order representation ability to formulate complex correlations among data by connecting two or more nodes through hyperedge modeling. Despite the well-studied adversarial attacks on Graph Neural Networks (GNN), there is few study on adversarial attacks against HGNN, which leads to a threat to the safety of HGNN applications. In this paper, we introduce HyperAttack, the first white-box adversarial attack framework against hypergraph neural networks. HyperAttack conducts a white-box structure attack by perturbing hyperedge link status towards the target node with the guidance of both gradients and integrated gradients. We evaluate HyperAttack on the widely-used Cora and PubMed datasets and three hypergraph neural networks with typical hypergraph modeling techniques. Compared to state-of-the-art white-box structural attack methods for GNN, HyperAttack achieves a 10-20X improvement in time efficiency while also increasing attack success rates by 1.3%-3.7%. The results show that HyperAttack can achieve efficient adversarial attacks that balance effectiveness and time costs.

Keywords

Cite

@article{arxiv.2302.12407,
  title  = {HyperAttack: Multi-Gradient-Guided White-box Adversarial Structure Attack of Hypergraph Neural Networks},
  author = {Chao Hu and Ruishi Yu and Binqi Zeng and Yu Zhan and Ying Fu and Quan Zhang and Rongkai Liu and Heyuan Shi},
  journal= {arXiv preprint arXiv:2302.12407},
  year   = {2023}
}

Comments

10+2pages,9figures

R2 v1 2026-06-28T08:48:29.132Z