Skip to main content

Ai-Gan: Attack-Inspired Generation Of Adversarial Examples

Tao Bai, Jun Zhao, Jinlin Zhu, Shoudong Han, Jiefeng Chen, Bo Li, Alex Kot

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
    Length: 00:07:31
22 Sep 2021

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.

Value-Added Bundle(s) Including this Product

More Like This

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00