Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks

Convolutional neural networks are vulnerable to small ℓp adversarial attacks, while the human visual system is not. Inspired by neural networks in the eye and the brain, we developed a novel artificial neural network model that recurrently collects data with a log-polar field of view that is controlled by attention. We demonstrate the effectiveness of this design as a defense against SPSA and PGD adversarial attacks. It also has beneficial properties observed in the animal visual system, such as reflex-like pathways for low-latency inference, fixed amount of computation independent of image size, and rotation and scale invariance. The code for experiments is available at https://gitlab.com/exwzd-public/kiritaniono2020.