ZK-GanDef: A GAN Based Zero Knowledge Adversarial Training Defense for Neural Networks

Guanxiong Liu, Issa Khalil, Abdallah Khreishah

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

17 Scopus citations

Abstract

Neural Network classifiers have been used successfully in a wide range of applications. However, their underlying assumption of attack free environment has been defied by adversarial examples. Researchers tried to develop defenses; however, existing approaches are still far from providing effective solutions to this evolving problem. In this paper, we design a generative adversarial net (GAN) based zero knowledge adversarial training defense, dubbed ZK-GanDef, which does not consume adversarial examples during training. Therefore, ZK-GanDef is not only efficient in training but also adaptive to new adversarial examples. This advantage comes at the cost of small degradation in test accuracy compared to full knowledge approaches. Our experiments show that ZK-GanDef enhances test accuracy on adversarial examples by up-To 49.17% compared to zero knowledge approaches. More importantly, its test accuracy is close to that of the state-of-The-Art full knowledge approaches (maximum degradation of 8.46%), while taking much less training time.

Original languageEnglish (US)
Title of host publicationProceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages64-75
Number of pages12
ISBN (Electronic)9781728100562
DOIs
StatePublished - Jun 2019
Event49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2019 - Portland, United States
Duration: Jun 24 2019Jun 27 2019

Publication series

NameProceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2019

Conference

Conference49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2019
Country/TerritoryUnited States
CityPortland
Period6/24/196/27/19

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Safety, Risk, Reliability and Quality
  • Hardware and Architecture

Keywords

  • Adversarial Training Defense
  • Generative Adversarial Nets
  • full knowledge training
  • zero knowledge training

Fingerprint

Dive into the research topics of 'ZK-GanDef: A GAN Based Zero Knowledge Adversarial Training Defense for Neural Networks'. Together they form a unique fingerprint.

Cite this