Defending Graph Convolutional Networks Against Adversarial Attacks

ICASSP 2020
Pages: 8469 - 8473
Published: May 4, 2020
Abstract
The interconnection of social, email, and media platforms enables adversaries to manipulate networked data and promote their malicious intents. This paper introduces graph neural network architectures that are robust to perturbed networked data. The novel network utilizes a randomization layer that performs link-dithering (LD) by adding or removing links with probabilities selected to boost robustness. The resultant link-dithered auxiliary...
Paper Details
Title
Defending Graph Convolutional Networks Against Adversarial Attacks
DOI
Published Date
May 4, 2020
Journal
Pages
8469 - 8473
Citation AnalysisPro
  • Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
  • Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.