Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness

ArXi:2605.07590v1 Announce Type: new Despite extensive progress in point cloud robustness, existing methods primarily improve performance through augmentation or defense mechanisms, while overlooking the geometric root cause of adversarial fragility. We hypothesize that adversarial vulnerability in 3D networks arises from a manifold misalignment between the latent geometry learned by the model and the intrinsic geometry of the underlying surface.