结构:图神经网络上基于结构的对抗性攻击

Hussain Hussain, Tomislav Duricic, E. Lex, D. Helic, M. Strohmaier, Roman Kern
{"title":"结构:图神经网络上基于结构的对抗性攻击","authors":"Hussain Hussain, Tomislav Duricic, E. Lex, D. Helic, M. Strohmaier, Roman Kern","doi":"10.1145/3465336.3475110","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":325072,"journal":{"name":"Proceedings of the 32nd ACM Conference on Hypertext and Social Media","volume":"4 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"Structack: Structure-based Adversarial Attacks on Graph Neural Networks\",\"authors\":\"Hussain Hussain, Tomislav Duricic, E. Lex, D. Helic, M. Strohmaier, Roman Kern\",\"doi\":\"10.1145/3465336.3475110\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"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.\",\"PeriodicalId\":325072,\"journal\":{\"name\":\"Proceedings of the 32nd ACM Conference on Hypertext and Social Media\",\"volume\":\"4 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-07-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 32nd ACM Conference on Hypertext and Social Media\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3465336.3475110\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 32nd ACM Conference on Hypertext and Social Media","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3465336.3475110","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

摘要

最近的研究表明,图神经网络(gnn)容易受到对图数据的对抗性攻击。常见的攻击方法通常是知情的,即它们可以访问节点属性(如标签和特征向量)的信息。在这项工作中,我们研究了不知情的对抗性攻击,攻击者只能访问图结构,但没有关于节点属性的信息。在这里,攻击者的目标是利用GNN模型对图数据所做的结构知识和假设。特别是,文献表明结构节点中心性和相似性对gnn的学习有很强的影响。因此,我们研究了中心性和相似性对gnn对抗性攻击的影响。我们证明了攻击者可以利用这些信息来降低gnn的性能,方法是专注于在低相似度和低中心性的节点之间注入链接。我们证明了基于结构的不知情攻击可以接近知情攻击的性能,同时计算效率更高。在我们的论文中,我们提出了一种新的gnn攻击策略,我们称之为Structack。Structack可以在有限的信息条件下成功地操纵gnn的性能,同时在严格的计算约束下运行。我们的工作有助于在图上构建更健壮的机器学习方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Structack: Structure-based Adversarial Attacks on Graph Neural Networks
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.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信