Incorporating Perceptual Prior to Improve Model's Adversarial Robustness

B.S. Vivek, Arya Baburaj, Ashutosh B Sathe, R. Venkatesh Babu

Abstract: Deep Neural Networks trained using human-annotated data are able to achieve human-like accuracy on many computer vision tasks such as classification, object recognition and segmentation. However, they are still far from being as robust as the human visual system. In this paper, we demonstrate that even models that are trained to be robust to random perturbations do not necessarily learn robust representations. We propose to address this by imposing a perception based prior on the learned representations to ensure that perceptually similar images have similar representations. We demonstrate that, although this training method does not use adversarial samples during training, it significantly improves the network’s robustness to single-step and multi-step adversarial attacks, thus validating our hypothesis that the network indeed learns more robust representations. Our proposed method provides a means of achieving adversarial robustness at no additional computational cost when compared to normal training.

Keywords: Representation learining, adversarial defense, robust neural networks