Parametric noise injection: Trainable randomness to improve deep neural network robustness against adversarial attack

Zhezhi He, Adnan Siraj Rakin, Deliang Fan

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

23 Scopus citations

Abstract

Recent developments in the field of Deep Learning have exposed the underlying vulnerability of Deep Neural Network (DNN) against adversarial examples. In image classification, an adversarial example is a carefully modified image that is visually imperceptible to the original image but can cause DNN model to misclassify it. Training the network with Gaussian noise is an effective technique to perform model regularization, thus improving model robustness against input variation. Inspired by this classical method, we explore to utilize the regularization characteristic of noise injection to improve DNN's robustness against adversarial attack. In this work, we propose Parametric-Noise-Injection (PNI) which involves trainable Gaussian noise injection at each layer on either activation or weights through solving the Min-Max optimization problem, embedded with adversarial training. These parameters are trained explicitly to achieve improved robustness. The extensive results show that our proposed PNI technique effectively improves the robustness against a variety of powerful white-box and black-box attacks such as PGD, C&W, FGSM, transferable attack, and ZOO attack. Last but not the least, PNI method improves both clean-and perturbed-data accuracy, in comparison to the state-of-the-art defense methods, which outperforms current unbroken PGD defense by 1.1% and 6.8% on clean-and perturbed-test data respectively, using ResNet-20 architecture.

Original languageEnglish (US)
Title of host publicationProceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
PublisherIEEE Computer Society
Pages588-597
Number of pages10
ISBN (Electronic)9781728132938
DOIs
StatePublished - Jun 2019
Externally publishedYes
Event32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 - Long Beach, United States
Duration: Jun 16 2019Jun 20 2019

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2019-June
ISSN (Print)1063-6919

Conference

Conference32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
CountryUnited States
CityLong Beach
Period6/16/196/20/19

Keywords

  • Categorization
  • Deep Learning
  • Optimization Methods
  • Recognition: Detection
  • Retrieval

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Parametric noise injection: Trainable randomness to improve deep neural network robustness against adversarial attack'. Together they form a unique fingerprint.

Cite this