To encourage future research, this survey summarizes the current progress on adversarial attack and defense techniques on point cloud classification.
To this end, we define 14 point cloud features and use multiple linear regression to examine whether these features can be used for model-free adversarial point prediction, and which combination of features is best suited for this purpose.
The proposed algorithm creates interpolated frames by first estimating motion vectors using unilateral (jointing forward and backward) and bilateral motion estimation.
Although 3D point cloud classification has recently been widely deployed in different application scenarios, it is still very vulnerable to adversarial attacks.
The obtained results show that it can perform successful attacks and achieve state-of-the-art results by only a limited number of point modifications while preserving the appearance of the point cloud.
It also reduces the model accuracy by an average of 73% on six datasets MNIST, FMNIST, SVHN, CIFAR10, CIFAR100, and ImageNet.