.png){kind=icon}
返回
Single-node attacks for fooling graph neural networks
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2022.09.115.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Graph neural networks (GNNs) have shown broad applicability in a variety of domains. These domains, e.g., social networks and product recommendations, are fertile ground for malicious users and behavior. In this paper, we show that GNNs are vulnerable to the extremely limited (and thus quite realistic) sce-narios of a single-node adversarial attack, where the perturbed node cannot be chosen by the attacker. That is, an attacker can force the GNN to classify any target node to a chosen label, by only slightly per-turbing the features or the neighbors list of another single arbitrary node in the graph, even when not being able to select that specific attacker node. When the adversary is allowed to select the attacker node, these attacks are even more effective. We demonstrate empirically that our attack is effective across var-ious common GNN types (e.g., GCN, GraphSAGE, GAT, GIN) and robustly optimized GNNs (e.g., Robust GCN, SM GCN, GAL, LAT-GCN), outperforming previous attacks across different real-world datasets both in a targeted and non-targeted attacks. Our code is available anonymously at https://github.com/gnnat tack/SINGLE. (c) 2022 Elsevier B.V. All rights reserved.
Keyword:
Graph neural networks
Adversarial robustness
Node classification
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
.png){kind=icon}
分享收藏分享收藏
查看更多内容