2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Imaging Without Borders

2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Login Paper Search My Schedule Paper Index Help

My ICIP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDARS-7.5
Paper Title AI-GAN: Attack-Inspired Generation of Adversarial Examples
Authors Tao Bai, Jun Zhao, Jinlin Zhu, Nanyang Technological University, Singapore; Shoudong Han, Huazhong University of Science and Technology, China; Jiefeng Chen, University of Wisconsin-Madison, United States; Bo Li, University of Illinois at Urbana-Champaign, United States; Alex Kot, Nanyang Technological University, United States
SessionARS-7: Image and Video Interpretation and Understanding 2
LocationArea H
Session Time:Wednesday, 22 September, 08:00 - 09:30
Presentation Time:Wednesday, 22 September, 08:00 - 09:30
Presentation Poster
Topic Image and Video Analysis, Synthesis, and Retrieval: Image & Video Interpretation and Understanding
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Deep neural networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding imperceptible perturbations to inputs. Recently different attacks and strategies have been proposed, but how to generate adversarial examples perceptually realistic and more efficiently remains unsolved. This paper proposes a novel framework called Attack-Inspired GAN (AI-GAN), where a generator, a discriminator, and an attacker are trained jointly. Once trained, it can generate adversarial perturbations efficiently given input images and target classes. Through extensive experiments on several popular datasets e.g. MNIST and CIFAR-10, AI-GAN achieves high attack success rates and reduces generation time significantly in various settings. Moreover, for the first time, AI-GAN successfully scales to complicated datasets e.g. CIFAR-100 with around $90\%$ success rates among all classes.