Generation of low distortion adversarial attacks via convex programming

Tianyun Zhang, Sijia Liu, Yanzhi Wang, Makan Fardad

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

Abstract

As deep neural networks (DNNs) achieve extraordinary performance in a wide range of tasks, testing their robustness under adversarial attacks becomes paramount. Adversarial attacks, also known as adversarial examples, are used to measure the robustness of DNNs and are generated by incorporating imperceptible perturbations into the input data with the intention of altering a DNN's classification. In prior work in this area, most of the proposed optimization based methods employ gradient descent to find adversarial examples. In this paper, we present an innovative method which generates adversarial examples via convex programming. Our experiment results demonstrate that we can generate adversarial examples with lower distortion and higher transferability than the C&W attack, which is the current state-of-the-art adversarial attack method for DNNs. We achieve 100% attack success rate on both the original undefended models and the adversarially-trained models. Our distortions of the L-inf attack are respectively 31% and 18% lower than the C&W attack for the best case and average case on the CIFAR-10 data set.

Original languageEnglish (US)
Title of host publicationProceedings - 19th IEEE International Conference on Data Mining, ICDM 2019
EditorsJianyong Wang, Kyuseok Shim, Xindong Wu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1486-1491
Number of pages6
ISBN (Electronic)9781728146034
DOIs
StatePublished - Nov 2019
Event19th IEEE International Conference on Data Mining, ICDM 2019 - Beijing, China
Duration: Nov 8 2019Nov 11 2019

Publication series

NameProceedings - IEEE International Conference on Data Mining, ICDM
Volume2019-November
ISSN (Print)1550-4786

Conference

Conference19th IEEE International Conference on Data Mining, ICDM 2019
CountryChina
CityBeijing
Period11/8/1911/11/19

Keywords

  • Adversarial attack
  • Convex programming
  • Deep neural networks

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Generation of low distortion adversarial attacks via convex programming'. Together they form a unique fingerprint.

  • Cite this

    Zhang, T., Liu, S., Wang, Y., & Fardad, M. (2019). Generation of low distortion adversarial attacks via convex programming. In J. Wang, K. Shim, & X. Wu (Eds.), Proceedings - 19th IEEE International Conference on Data Mining, ICDM 2019 (pp. 1486-1491). [8970743] (Proceedings - IEEE International Conference on Data Mining, ICDM; Vol. 2019-November). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICDM.2019.00195