Locally optimal detection of adversarial inputs to image classifiers

Pierre Moulin, Amish Goel

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

Abstract

Deep neural networks achieve state-of-the-art performance for image classification and other tasks but are easily fooled by forgeries which slightly modify a legitimate image in a specific direction and are visually indistinguishable from the original. This presents a security risk for applications such as driverless transportation systems. We formulate detection of such forgeries as a watermark detection problem and derive locally optimal statistical tests for identifying them. Motivated by this optimal structure, we present a procedure for learning a forgery detector from a training set. The reliability of our forgery detector is assessed for several image classification tasks.

Original languageEnglish (US)
Title of host publication2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages459-464
Number of pages6
ISBN (Electronic)9781538605608
DOIs
StatePublished - Sep 5 2017
Event2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017 - Hong Kong, Hong Kong
Duration: Jul 10 2017Jul 14 2017

Publication series

Name2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017

Other

Other2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017
CountryHong Kong
CityHong Kong
Period7/10/177/14/17

ASJC Scopus subject areas

  • Computer Science Applications
  • Media Technology

Fingerprint Dive into the research topics of 'Locally optimal detection of adversarial inputs to image classifiers'. Together they form a unique fingerprint.

  • Cite this

    Moulin, P., & Goel, A. (2017). Locally optimal detection of adversarial inputs to image classifiers. In 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017 (pp. 459-464). [8026257] (2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMEW.2017.8026257