Cycle-Consistent Adversarial GAN: the integration of adversarial attack and defense
This addresses the vulnerability of deep learning models to adversarial attacks, offering a combined approach for improved robustness, though it appears incremental by building on existing GAN and adversarial example research.
The paper tackles the problem of adversarial examples in deep neural networks by proposing Cycle-Consistent Adversarial GAN (CycleAdvGAN), which integrates attack and defense to generate adversarial perturbations and recover clean instances, achieving state-of-the-art results on MNIST and CIFAR10 datasets.
In image classification of deep learning, adversarial examples where inputs intended to add small magnitude perturbations may mislead deep neural networks (DNNs) to incorrect results, which means DNNs are vulnerable to them. Different attack and defense strategies have been proposed to better research the mechanism of deep learning. However, those research in these networks are only for one aspect, either an attack or a defense, not considering that attacks and defenses should be interdependent and mutually reinforcing, just like the relationship between spears and shields. In this paper, we propose Cycle-Consistent Adversarial GAN (CycleAdvGAN) to generate adversarial examples, which can learn and approximate the distribution of original instances and adversarial examples. For CycleAdvGAN, once the Generator and are trained, can generate adversarial perturbations efficiently for any instance, so as to make DNNs predict wrong, and recovery adversarial examples to clean instances, so as to make DNNs predict correct. We apply CycleAdvGAN under semi-white box and black-box settings on two public datasets MNIST and CIFAR10. Using the extensive experiments, we show that our method has achieved the state-of-the-art adversarial attack method and also efficiently improve the defense ability, which make the integration of adversarial attack and defense come true. In additional, it has improved attack effect only trained on the adversarial dataset generated by any kind of adversarial attack.