Transferable and Undefendable Point Cloud Attacks via Medial Axis Transform
This addresses the need for more effective adversarial attacks to evaluate and improve the robustness of 3D deep learning models, representing a novel method for a known bottleneck.
The paper tackles the problem of limited transferability and robustness in adversarial attacks on 3D point clouds by proposing MAT-Adv, a framework that perturbs medial axis transform representations to induce structural-level adversarial characteristics, resulting in significant outperformance over state-of-the-art methods in both transferability and undefendability.
Studying adversarial attacks on point clouds is essential for evaluating and improving the robustness of 3D deep learning models. However, most existing attack methods are developed under ideal white-box settings and often suffer from limited transferability to unseen models and insufficient robustness against common defense mechanisms. In this paper, we propose MAT-Adv, a novel adversarial attack framework that enhances both transferability and undefendability by explicitly perturbing the medial axis transform (MAT) representations, in order to induce inherent adversarialness in the resulting point clouds. Specifically, we employ an autoencoder to project input point clouds into compact MAT representations that capture the intrinsic geometric structure of point clouds. By perturbing these intrinsic representations, MAT-Adv introduces structural-level adversarial characteristics that remain effective across diverse models and defense strategies. To mitigate overfitting and prevent perturbation collapse, we incorporate a dropout strategy into the optimization of MAT perturbations, further improving transferability and undefendability. Extensive experiments demonstrate that MAT-Adv significantly outperforms existing state-of-the-art methods in both transferability and undefendability. Codes will be made public upon paper acceptance.