Joint Adversarial Attack: An Effective Approach to Evaluate Robustness of 3D Object Tracking

Deep neural networks (DNNs) have widely been used in 3D object tracking, thanks to its superior capabilities to learn from geometric training samples and locate tracking targets. Although the DNN based trackers show vulnerability to adversarial examples, their robustness in real-world scenarios with potentially complex data defects has rarely been studied. To this end, a joint adversarial attack method against 3D object tracking is proposed, which simulates defects of the point cloud data in the form of point filtration and perturbation simultaneously. Specifically, a voxel-based point filtration module is designed to filter points of the tracking template, which is described by the voxel-wise binary distribution regarding the density of the point cloud. Furthermore, a voxel-based point perturbation module adds voxel-wise perturbations to the filtered template, whose direction is constrained by local geometrical information of the template. Experiments conducted on popular 3D trackers demonstrate that the proposed joint attack have decreased the success and precision of existing 3D trackers by 30.2% and 35.4% respectively in average, which made an improvement of 30.5% over existing attack methods.