Improving adversarial robustness by enforcing local and global compactness

Anh Bui, Trung Le, He Zhao, Paul Montague, Olivier deVel, Tamas Abraham, Dinh Phung

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

2 Citations (Scopus)


The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges as the most successful method that consistently resists a wide range of attacks. In this work, based on an observation from a previous study that the representations of a clean data example and its adversarial examples become more divergent in higher layers of a deep neural net, we propose the Adversary Divergence Reduction Network which enforces local/global compactness and the clustering assumption over an intermediate layer of a deep neural network. We conduct comprehensive experiments to understand the isolating behavior of each component (i.e., local/global compactness and the clustering assumption) and compare our proposed model with state-of-the-art adversarial training methods. The experimental results demonstrate that augmenting adversarial training with our proposed components can further improve the robustness of the network, leading to higher unperturbed and adversarial predictive performances.

Original languageEnglish
Title of host publicationComputer Vision – ECCV 2020
Subtitle of host publication16th European Conference Glasgow, UK, August 23–28, 2020 Proceedings, Part XXVII
EditorsAndrea Vedaldi, Horst Bischof, Thomas Brox, Jan-Michael Frahm
Place of PublicationCham Switzerland
Number of pages15
ISBN (Electronic)9783030585839
ISBN (Print)9783030585822
Publication statusPublished - 2020
EventEuropean Conference on Computer Vision 2020 - Glasgow, United Kingdom
Duration: 23 Aug 202028 Aug 2020
Conference number: 16th (Proceedings) (Website)

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


ConferenceEuropean Conference on Computer Vision 2020
Abbreviated titleECCV 2020
Country/TerritoryUnited Kingdom
Internet address


  • Adversarial robustness
  • Clustering assumption
  • Global compactness
  • Local compactness

Cite this