Local Aggressive Adversarial Attacks on 3D Point Cloud
This work improves adversarial attack effectiveness for 3D point cloud models, which is important for security and robustness in applications like autonomous driving and robotics, though it is incremental as it builds on existing methods.
The paper tackles the problem of generating adversarial examples for 3D point clouds by addressing inefficiencies in global optimization methods, proposing a local aggressive attack (L3A) that selects salient points and uses aggressive optimization strategies, achieving state-of-the-art performance on models like PointNet, PointNet++, and DGCNN.
Deep neural networks are found to be prone to adversarial examples which could deliberately fool the model to make mistakes. Recently, a few of works expand this task from 2D image to 3D point cloud by using global point cloud optimization. However, the perturbations of global point are not effective for misleading the victim model. First, not all points are important in optimization toward misleading. Abundant points account considerable distortion budget but contribute trivially to attack. Second, the multi-label optimization is suboptimal for adversarial attack, since it consumes extra energy in finding multi-label victim model collapse and causes instance transformation to be dissimilar to any particular instance. Third, the independent adversarial and perceptibility losses, caring misclassification and dissimilarity separately, treat the updating of each point equally without a focus. Therefore, once perceptibility loss approaches its budget threshold, all points would be stock in the surface of hypersphere and attack would be locked in local optimality. Therefore, we propose a local aggressive adversarial attacks (L3A) to solve above issues. Technically, we select a bunch of salient points, the high-score subset of point cloud according to gradient, to perturb. Then a flow of aggressive optimization strategies are developed to reinforce the unperceptive generation of adversarial examples toward misleading victim models. Extensive experiments on PointNet, PointNet++ and DGCNN demonstrate the state-of-the-art performance of our method against existing adversarial attack methods.