Timezone: »
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.
Author Information
Jiachen Sun (University of Michigan)
Yulong Cao (University of Michigan)
Christopher B Choy (Stanford University)
Zhiding Yu (NVIDIA)
Anima Anandkumar (NVIDIA/Caltech)
Zhuoqing Morley Mao (University of Michigan)
Chaowei Xiao (University of Michigan, Ann Arbor)
I am Chaowei Xiao, a third year PhD student in CSE Department, University of Michigan, Ann Arbor. My advisor is Professor Mingyan Liu . I obtained my bachelor's degree in School of Software from Tsinghua University in 2015, advised by Professor Yunhao Liu, Professor Zheng Yang and Dr. Lei Yang. I was also a visiting student at UC Berkeley in 2018, advised by Professor Dawn Song and Professor Bo Li. My research interest includes adversarial machine learning.
More from the Same Authors
-
2022 : Retrieval-based Controllable Molecule Generation »
Jack Wang · Weili Nie · Zhuoran Qiao · Chaowei Xiao · Richard Baraniuk · Anima Anandkumar -
2022 : MoleculeCLIP: Learning Transferable Molecule Multi-Modality Models via Natural Language »
Shengchao Liu · Weili Nie · Chengpeng Wang · Jiarui Lu · Zhuoran Qiao · Ling Liu · Jian Tang · Anima Anandkumar · Chaowei Xiao -
2022 : Calibration of Large Neural Weather Models »
Andre Graubner · Kamyar Azizzadenesheli · Jaideep Pathak · Morteza Mardani · Mike Pritchard · Karthik Kashinath · Anima Anandkumar -
2022 : FourCastNet: A practical introduction to a state-of-the-art deep learning global weather emulator »
Jaideep Pathak · Shashank Subramanian · Peter Harrington · Thorsten Kurth · Andre Graubner · Morteza Mardani · David Hall · Karthik Kashinath · Anima Anandkumar -
2022 : Robust Trajectory Prediction against Adversarial Attacks »
Yulong Cao · Danfei Xu · Xinshuo Weng · Zhuoqing Morley Mao · Anima Anandkumar · Chaowei Xiao · Marco Pavone -
2022 : AdvDO: Realistic Adversarial Attacks for Trajectory Prediction »
Yulong Cao · Chaowei Xiao · Anima Anandkumar · Danfei Xu · Marco Pavone -
2023 Poster: On the Exploitability of Instruction Tuning »
Manli Shu · Jiongxiao Wang · Jonas Geiping · Chaowei Xiao · Tom Goldstein -
2022 : Calibration of Large Neural Weather Models »
Andre Graubner · Kamyar Azizzadenesheli · Jaideep Pathak · Morteza Mardani · Mike Pritchard · Karthik Kashinath · Anima Anandkumar -
2022 Workshop: Trustworthy and Socially Responsible Machine Learning »
Huan Zhang · Linyi Li · Chaowei Xiao · J. Zico Kolter · Anima Anandkumar · Bo Li -
2022 Poster: Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models »
Manli Shu · Weili Nie · De-An Huang · Zhiding Yu · Tom Goldstein · Anima Anandkumar · Chaowei Xiao -
2022 Poster: Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models »
Boxin Wang · Wei Ping · Chaowei Xiao · Peng Xu · Mostofa Patwary · Mohammad Shoeybi · Bo Li · Anima Anandkumar · Bryan Catanzaro -
2021 Poster: Controllable and Compositional Generation with Latent-Space Energy-Based Models »
Weili Nie · Arash Vahdat · Anima Anandkumar -
2021 Poster: AugMax: Adversarial Composition of Random Augmentations for Robust Training »
Haotao Wang · Chaowei Xiao · Jean Kossaifi · Zhiding Yu · Anima Anandkumar · Zhangyang Wang -
2021 Poster: Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds »
Yujia Huang · Huan Zhang · Yuanyuan Shi · J. Zico Kolter · Anima Anandkumar -
2021 Poster: Coupled Segmentation and Edge Learning via Dynamic Graph Propagation »
Zhiding Yu · Rui Huang · Wonmin Byeon · Sifei Liu · Guilin Liu · Thomas Breuel · Anima Anandkumar · Jan Kautz -
2021 Poster: Long-Short Transformer: Efficient Transformers for Language and Vision »
Chen Zhu · Wei Ping · Chaowei Xiao · Mohammad Shoeybi · Tom Goldstein · Anima Anandkumar · Bryan Catanzaro -
2021 Poster: SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers »
Enze Xie · Wenhai Wang · Zhiding Yu · Anima Anandkumar · Jose M. Alvarez · Ping Luo -
2020 Poster: Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations »
Huan Zhang · Hongge Chen · Chaowei Xiao · Bo Li · Mingyan Liu · Duane Boning · Cho-Jui Hsieh -
2020 Spotlight: Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations »
Huan Zhang · Hongge Chen · Chaowei Xiao · Bo Li · Mingyan Liu · Duane Boning · Cho-Jui Hsieh -
2017 Poster: Deep Hyperspherical Learning »
Weiyang Liu · Yan-Ming Zhang · Xingguo Li · Zhiding Yu · Bo Dai · Tuo Zhao · Le Song -
2017 Spotlight: Deep Hyperspherical Learning »
Weiyang Liu · Yan-Ming Zhang · Xingguo Li · Zhiding Yu · Bo Dai · Tuo Zhao · Le Song -
2016 Poster: Universal Correspondence Network »
Christopher B Choy · Manmohan Chandraker · JunYoung Gwak · Silvio Savarese -
2016 Oral: Universal Correspondence Network »
Christopher B Choy · Manmohan Chandraker · JunYoung Gwak · Silvio Savarese