A General Framework for Adversarial Examples with Objectives

Journal Article

Images perturbed subtly to be misclassified by neural networks, called adversarial examples , have emerged as a technically deep challenge and an important concern for several application domains. Most research on adversarial examples takes as its only constraint that the perturbed images are similar to the originals. However, real-world application of these ideas often requires the examples to satisfy additional objectives, which are typically enforced through custom modifications of the perturbation process. In this article, we propose adversarial generative nets (AGNs), a general methodology to train a generator neural network to emit adversarial examples satisfying desired objectives. We demonstrate the ability of AGNs to accommodate a wide range of objectives, including imprecise ones difficult to model, in two application domains. In particular, we demonstrate physical adversarial examples—eyeglass frames designed to fool face recognition—with better robustness, inconspicuousness, and scalability than previous approaches, as well as a new attack to fool a handwritten-digit classifier.

Full Text

Duke Authors

Cited Authors

  • Sharif, M; Bhagavatula, S; Bauer, L; Reiter, MK

Published Date

  • July 19, 2019

Published In

Volume / Issue

  • 22 / 3

Start / End Page

  • 1 - 30

Published By

Electronic International Standard Serial Number (EISSN)

  • 2471-2574

International Standard Serial Number (ISSN)

  • 2471-2566

Digital Object Identifier (DOI)

  • 10.1145/3317611

Language

  • en