2022/08/21 by J. F. Sun, Sun, Jiachen, Weili Nie +7
Agricultural and Biological Sciences · Computer Science · #Adversarial Robustness in Machine Learning #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Forensic Entomology and Diptera Studies #Machine Learning (cs.LG)
paper · pdf · doi:10.48550/arxiv.2208.09801
openalex publication_date 2022/08/21 · openalex created_date 2022/08/24 · openalex updated_date 2026/07/28
3D Point cloud is becoming a critical data representation in many real-world applications like autonomous driving, robotics, and medical imaging. Although the success of deep learning further accelerates the adoption of 3D point clouds in the physical world, deep learning is notorious for its vulnerability to adversarial attacks. In this work, we first identify that the state-of-the-art empirical defense, adversarial training, has a major limitation in applying to 3D point cloud models due to gradient obfuscation. We further propose PointDP, a purification strategy that leverages diffusion models to defend against 3D adversarial attacks. We extensively evaluate PointDP on six representative 3D point cloud architectures, and leverage 10+ strong and adaptive attacks to demonstrate its lower-bound robustness. Our evaluation shows that PointDP achieves significantly better robustness than state-of-the-art purification methods under strong attacks. Results of certified defenses on randomized smoothing combined with PointDP will be included in the near future.