DeepInsight : Topology Changes Assisting Detection of Adversarial Samples on Graphs

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

1 Scopus Citations
View graph of relations

Author(s)

  • Junhao Zhu
  • Jinhuan Wang
  • Yalu Shan
  • Shanqing Yu
  • Qi Xuan

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)76-88
Number of pages13
Journal / PublicationIEEE Transactions on Computational Social Systems
Volume11
Issue number1
Online published27 Oct 2022
Publication statusPublished - Feb 2024

Abstract

With the rapid development of artificial intelligence, a number of machine learning algorithms, such as graph neural networks (GNNs), have been proposed to facilitate network analysis or graph data mining. Although effective, recent studies show that these advanced methods may suffer from adversarial attacks, i.e., they may lose effectiveness when only a small fraction of links are unexpectedly changed. This article investigates three well-known adversarial attack methods, i.e., Nettack, Meta Attack, and GradArgmax. It is found that different attack methods have their specific attack preferences on changing the target network structures. Such attack patterns are further verified by experimental results on some real-world networks, revealing that, generally, the top-4 most important network attributes on detecting adversarial samples suffice to explain the preference of an attack method. Based on these findings, the network attributes are utilized to design machine learning models for adversarial sample detection and attack method recognition with outstanding performance. © 2022 IEEE.

Research Area(s)

  • Adversarial attack, adversarial defense, Anomaly detection, Detectors, Feature extraction, graph data mining, Image edge detection, network structure, node classification, Security, social network, Task analysis, Topology

Citation Format(s)

DeepInsight: Topology Changes Assisting Detection of Adversarial Samples on Graphs. / Zhu, Junhao; Wang, Jinhuan; Shan, Yalu et al.
In: IEEE Transactions on Computational Social Systems, Vol. 11, No. 1, 02.2024, p. 76-88.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review