A Caltech Library Service

Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions

Sun, Jiachen and Cao, Yulong and Choy, Christopher and Yu, Zhiding and Anandkumar, Anima and Mao, Zhuqing M. and Xiao, Chaowei (2021) Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions. In: 35th Conference on Neural Information Processing Systems (NeurIPS 2021). Neural Information Processing Foundation , La Jolla, CA, pp. 1-15. ISBN 9781713845393.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


3D point cloud data is increasingly used in safety-critical applications such as autonomous driving. Thus, the robustness of 3D deep learning models against adversarial attacks becomes a major consideration. In this paper, we systematically study the impact of various self-supervised learning proxy tasks on different architectures and threat models for 3D point clouds with adversarial training. Specifically, we study MLP-based (PointNet), convolution-based (DGCNN), and transformer-based (PCT) 3D architectures. Through extensive experimentation, we demonstrate that appropriate applications of self-supervision can significantly enhance the robustness in 3D point cloud recognition, achieving considerable improvements compared to the standard adversarial training baseline. Our analysis reveals that local feature learning is desirable for adversarial robustness in point clouds since it limits the adversarial propagation between the point-level input perturbations and the model's final output. This insight also explains the success of DGCNN and the jigsaw proxy task in achieving stronger 3D adversarial robustness.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Sun, Jiachen0000-0003-1170-4735
Cao, Yulong0000-0003-3007-2550
Choy, Christopher0000-0002-6566-3193
Anandkumar, Anima0000-0002-6974-6797
Xiao, Chaowei0000-0002-7043-4926
Additional Information:We appreciate our area chairs and anonymous reviewers for their insightful comments. We thank Qingzhao Zhang for proofreading our manuscript. Jiachen Sun thanks Zhao Su for her considerate care and help during COVIID-19. This project is partially supported by NSF grants CMMI-2038215 and CNS-1930041.
Funding AgencyGrant Number
Record Number:CaltechAUTHORS:20221222-232011120
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:118601
Deposited By: George Porter
Deposited On:23 Dec 2022 16:30
Last Modified:23 Dec 2022 16:30

Repository Staff Only: item control page