Provable Defense Against Clustering Attacks on 3D Point Clouds

AAAI Workshop AdvML 2022 · Dishanika Dewani Denipitiyage, Thalaiyasingam Ajanthan, Parameswaran Kamalaruban, Adrian Weller ·

Lately, the literature on adversarial robustness spans from images to other domains such as point clouds. In this work, we consider clustering attacks on 3D point clouds and devise a provable defense mechanism to counter them. Specifically, we adopt a randomized smoothing strategy for 3D point clouds and derive a robustness certificate based on the cluster radius rather than the number of adversarial points. Our experiments on ModelNet40 and ScanObjectNN datasets using the PointNet classifier demonstrate the effectiveness of our defense mechanism against targeted and untargeted clustering attacks with a large number of adversarial points.

PDF Abstract