Defending Graph Convolutional Networks Against Adversarial Attacks

Vassilis N. Ioannidis, Georgios B. Giannakis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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 graphs are leveraged by an adaptive (A)GCN that performs SSL. The proposed robust LD-AGCN achieves performance gains relative to GCNs under perturbed network data.

Original languageEnglish (US)
Title of host publication2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages8469-8473
Number of pages5
ISBN (Electronic)9781509066315
DOIs
StatePublished - May 2020
Event2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Barcelona, Spain
Duration: May 4 2020May 8 2020

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2020-May
ISSN (Print)1520-6149

Conference

Conference2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
CountrySpain
CityBarcelona
Period5/4/205/8/20

Keywords

  • Deep neural networks
  • dithering
  • graph convolutional networks
  • graph signals
  • robust learning

Fingerprint Dive into the research topics of 'Defending Graph Convolutional Networks Against Adversarial Attacks'. Together they form a unique fingerprint.

  • Cite this

    Ioannidis, V. N., & Giannakis, G. B. (2020). Defending Graph Convolutional Networks Against Adversarial Attacks. In 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings (pp. 8469-8473). [9054325] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2020-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP40776.2020.9054325