Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusion
This addresses security threats in safety-critical applications like autonomous driving by providing a generalized defense against adversarial perturbations.
The paper tackles the vulnerability of deep 3D point cloud models to adversarial attacks by introducing Ada3Diff, a distortion-aware defense framework that uses adaptive diffusion to restore perturbed point clouds to a clean distribution, enhancing robustness against various attacks.
Deep 3D point cloud models are sensitive to adversarial attacks, which poses threats to safety-critical applications such as autonomous driving. Robust training and defend-by-denoising are typical strategies for defending adversarial perturbations. However, they either induce massive computational overhead or rely heavily upon specified priors, limiting generalized robustness against attacks of all kinds. To remedy it, this paper introduces a novel distortion-aware defense framework that can rebuild the pristine data distribution with a tailored intensity estimator and a diffusion model. To perform distortion-aware forward diffusion, we design a distortion estimation algorithm that is obtained by summing the distance of each point to the best-fitting plane of its local neighboring points, which is based on the observation of the local spatial properties of the adversarial point cloud. By iterative diffusion and reverse denoising, the perturbed point cloud under various distortions can be restored back to a clean distribution. This approach enables effective defense against adaptive attacks with varying noise budgets, enhancing the robustness of existing 3D deep recognition models.