Manigen: A manifold aided black-box generator of adversarial examples

Guanxiong Liu, Issa Khalil, Abdallah Khreishah, Abdulelah Algosaibi, Adel Aldalbahi, Mohammed Alnaeem, Abdulaziz Alhumam, Muhammad Anan

Research output: Contribution to journalArticlepeer-review

Abstract

From recent research work, it has been shown that neural network (NN) classifiers are vulnerable to adversarial examples which contain special perturbations that are ignored by human eyes while can mislead NN classifiers. In this paper, we propose a practical black-box adversarial example generator, dubbed ManiGen. ManiGen does not require any knowledge of the inner state of the target classifier. It generates adversarial examples by searching along the manifold, which is a concise representation of input data. Through extensive set of experiments on different datasets, we show that (1) adversarial examples generated by ManiGen can mislead standalone classifiers by being as successful as the state-of-the-art white- box generator, Carlini, and (2) adversarial examples generated by ManiGen can more effectively attack classifiers with state-of-the-art defenses.

Original languageEnglish (US)
Pages (from-to)197086-197096
Number of pages11
JournalIEEE Access
Volume8
DOIs
StatePublished - 2020

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Keywords

  • Adversarial examples
  • Machine learning
  • Manifold
  • Neural network

Fingerprint Dive into the research topics of 'Manigen: A manifold aided black-box generator of adversarial examples'. Together they form a unique fingerprint.

Cite this