Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/156472
Title: Class-based attack on graph convolution network
Authors: He, HeFei
Keywords: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Issue Date: 2022
Publisher: Nanyang Technological University
Source: He, H. (2022). Class-based attack on graph convolution network. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/156472
Project: SCSE21-0018
Abstract: Prevalent use of graph structure data for classification tasks has brought attention to the robustness of graph convolutional networks. Recent study has been shown that graph convolutional networks are vulnerable to adversary attacks, causing a severe threat to real world application. In this report, we have conducted two types of untargeted attack on the graph convolutional network by injecting the fake node. The perturbation of fake nodes was based on the corresponding feature of the class and connected to different classes(dConnClass) or the same class(sConnClass), aiming to minimise the classification accuracy of the graph convolutional network.
URI: https://hdl.handle.net/10356/156472
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
FYP_report.pdf
  Restricted Access
1.51 MBAdobe PDFView/Open

Page view(s)

17
Updated on May 17, 2022

Download(s)

4
Updated on May 17, 2022

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.