超图
对抗制
计算机科学
节点(物理)
人工神经网络
深层神经网络
代表(政治)
图形
深度学习
理论计算机科学
人工智能
数学
工程类
离散数学
结构工程
政治
法学
政治学
作者
Chao Hu,Ruishi Yu,Binqi Zeng,Zhan Yu,Ying Fu,Quan Zhang,Rongkai Liu,Heyuan Shi
出处
期刊:Cornell University - arXiv
日期:2023-01-01
被引量:1
标识
DOI:10.48550/arxiv.2302.12407
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI