Adversarial attack against urban scene segmentation for autonomous vehicles

Understanding the environment is crucial for autonomous vehicles to make correct driving decisions. In particular, urban scene segmentation is a significant integral module commonly equipped in the perception system of autonomous vehicles to understand the real scene like a human. Any mis-segmentation of the driving scenario can potentially result in uncontrollable consequences such as serious accidents or the exception of the perception system. In this paper, we investigate the vulnerability of the popular scene segmentation models designed with the backbones of deep neural networks (DNNs), which have been shown to be sensitive to adversarial attacks. Specifically, we propose an iterative projected gradient based attack method that can effectively fool several DNN based segmentation models with a remarkably higher attacking successful rate and much smaller adversarial perturbations. Moreover, we also develop an adversarial training algorithm with mini-max optimization style to enrich the robustness of the scene segmentation models. Extensive experiments on the Cityscape benchmark dataset consisting of large-scale urban scene images for autonomous vehicles demonstrate the effectiveness of our proposed attack method, as well as the benefit of the adversarial training scheme for the scene segmentation models.