Poster: Characterizing adversarial subspaces by mutual information

Chia Yi Hsu, Pin Yu Chen, Chia Mu Yu

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

Abstract

Deep learning is well-known for its great performances on images classification, object detection, and natural language processing. However, the recent research has demonstrated that visually indistinguishable images called adversarial examples can successfully fool neural networks by carefully crafting. In this paper, we design a detector named MID, calculating mutual information to characterize adversarial subspaces. Meanwhile, we use the defense framework called MagNet and mount the detector MID on it. Experimental results show that projected gradient descent (PGD), basic iterative method (BIM), Carlini and Wanger's attack (C&W attack) and elastic-net attack to deep neural network (elastic-net and L1 rules) can be effectively defended by our method.

Original languageEnglish
Title of host publicationAsiaCCS 2019 - Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security
PublisherAssociation for Computing Machinery, Inc
Pages667-669
Number of pages3
ISBN (Electronic)9781450367523
DOIs
StatePublished - 2 Jul 2019
Event2019 ACM Asia Conference on Computer and Communications Security, AsiaCCS 2019 - Auckland, New Zealand
Duration: 9 Jul 201912 Jul 2019

Publication series

NameAsiaCCS 2019 - Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security

Conference

Conference2019 ACM Asia Conference on Computer and Communications Security, AsiaCCS 2019
CountryNew Zealand
CityAuckland
Period9/07/1912/07/19

Keywords

  • Adversarial examples
  • Neural networks

Fingerprint Dive into the research topics of 'Poster: Characterizing adversarial subspaces by mutual information'. Together they form a unique fingerprint.

  • Cite this

    Hsu, C. Y., Chen, P. Y., & Yu, C. M. (2019). Poster: Characterizing adversarial subspaces by mutual information. In AsiaCCS 2019 - Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security (pp. 667-669). (AsiaCCS 2019 - Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security). Association for Computing Machinery, Inc. https://doi.org/10.1145/3321705.3331002