SymAttack: Symmetry-aware Imperceptible Adversarial Attacks on 3D Point Clouds
Authors: 
Keke Tang, Zhensu Wang, Weilong Peng, Lujie Huang, Le Wang, Peican Zhu, Wenping Wang, Zhihong TianAuthors Info & Claims
Pages 3131 - 3140
Abstract
Adversarial attacks on point clouds are crucial for assessing and improving the adversarial robustness of 3D deep learning models. Despite leveraging various geometric constraints, current adversarial attack strategies often suffer from inadequate imperceptibility. Given that adversarial perturbations tend to disrupt the inherent symmetry in objects, we recognize this disruption as the primary cause of the lack of imperceptibility in these attacks. In this paper, we introduce a novel framework, symmetry-aware imperceptible adversarial attacks on 3D point clouds (SymAttack), to address this issue. Our approach starts by identifying part- and patch-level symmetry elements, and grouping points based on semantic and Euclidean distances, respectively. During the adversarial attack iterations, we intentionally adjust the perturbation vectors on symmetric points relative to their symmetry plane. By preserving symmetry within the attack process, SymAttack significantly enhances imperceptibility. Extensive experiments validate the effectiveness of SymAttack in generating imperceptible adversarial point clouds, demonstrating its superiority over the state-of-the-art methods.
References
[1]
Nicholas Carlini and David Wagner. 2017. Towards evaluating the robustness of neural networks. In IEEE Symposium on Security and Privacy. 39--57.
[2]
Lifang Chen and Qian Zhang. 2022. DDGCN: graph convolution network based on direction and distance for point cloud learning. The Visual Computer (2022), 1--11.
[3]
Yuhong Chen, Weilong Peng, Keke Tang, Asad Khan, Guodong Wei, and Meie Fang. 2022. Pyrapvconv: efficient 3d point cloud perception with pyramid voxel convolution and sharable attention. Computational Intelligence and Neuroscience, Vol. 2022, 1 (2022), 2286818.
[4]
Xiaoyi Dong, Dongdong Chen, Hang Zhou, Gang Hua, Weiming Zhang, and Nenghai Yu. 2020. Self-Robust 3D Point Recognition via Gather-Vector Guidance. In CVPR. 11513--11521.
[5]
Aleksandrs Ecins, Cornelia Fermüller, and Yiannis Aloimonos. 2016. Cluttered scene segmentation using the symmetry constraint. In ICRA. IEEE, 2271--2278.
[6]
Haoqiang Fan, Hao Su, and Leonidas J Guibas. 2017. A point set generation network for 3d object reconstruction from a single image. In CVPR. 605--613.
[7]
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In NeurIPS, Vol. 27.
[8]
Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and harnessing adversarial examples. In ICLR.
[9]
Yulan Guo, Hanyun Wang, Qingyong Hu, Hao Liu, Li Liu, and Mohammed Bennamoun. 2020. Deep learning for 3d point clouds: A survey. IEEE TPAMI, Vol. 43, 12 (2020), 4338--4364.
[10]
Qidong Huang, Xiaoyi Dong, Dongdong Chen, Hang Zhou, Weiming Zhang, and Nenghai Yu. 2022. Shape-invariant 3d adversarial point clouds. In CVPR. 15335--15344.
[11]
Anastasia Ioannidou, Elisavet Chatzilari, Spiros Nikolopoulos, and Ioannis Kompatsiaris. 2017. Deep learning advances in computer vision with 3d data: A survey. ACM computing surveys, Vol. 50, 2 (2017), 1--38.
[12]
Michael Kazhdan, Thomas Funkhouser, and Szymon Rusinkiewicz. 2004. Symmetry descriptors and 3D shape matching. In SGP. 115--123.
[13]
Jaeyeon Kim, Binh-Son Hua, Thanh Nguyen, and Sai-Kit Yeung. 2021. Minimal adversarial examples for deep learning on 3d point clouds. In ICCV. 7797--7806.
[14]
Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature, Vol. 521, 7553 (2015), 436--444.
[15]
Kibok Lee, Zhuoyuan Chen, Xinchen Yan, Raquel Urtasun, and Ersin Yumer. 2020. Shapeadv: Generating shape-aware adversarial 3d point clouds. arXiv preprint arXiv:2005.11626 (2020).
[16]
Qi Li, Xingyu Li, Xiaodong Cui, Keke Tang, and Peican Zhu. 2023. Hept attack: heuristic perpendicular trial for hard-label attacks under limited query budgets. In CIKM. 4064--4068.
[17]
Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, and Baoquan Chen. 2018. PointCNN: Convolution on ?-transformed points. In NeurIPS. 820--830.
[18]
Daizong Liu and Wei Hu. 2022. Imperceptible transfer attack and defense on 3d point cloud classification. IEEE TPAMI, Vol. 45, 4 (2022), 4727--4746.
[19]
Daniel Liu, Ronald Yu, and Hao Su. 2019. Extending adversarial attacks and defenses to deep 3d point cloud classifiers. In ICIP. 2279--2283.
[20]
Daniel Maturana and Sebastian Scherer. 2015. Voxnet: A 3d convolutional neural network for real-time object recognition. In IROS. 922--928.
[21]
P. Minovic, S. Ishikawa, and K. Kato. 1993. Symmetry identification of a 3-D object represented by octree. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 15, 5 (1993), 507--514. https://doi.org/10.1109/34.211472
[22]
Niloy J Mitra, Mark Pauly, Michael Wand, and Duygu Ceylan. 2013. Symmetry in 3d geometry: Extraction and applications. In Computer Graphics Forum, Vol. 32. 1--23.
[23]
Khan Muhammad, Amin Ullah, Jaime Lloret, Javier Del Ser, and Victor Hugo C de Albuquerque. 2020. Deep learning for safe autonomous driving: Current challenges and future directions. IEEE Transactions on Intelligent Transportation Systems, Vol. 22, 7 (2020), 4316--4336.
[24]
Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. In NeurIPS, Vol. 32.
[25]
Charles R Qi, Hao Su, Kaichun Mo, and Leonidas J Guibas. 2017. Pointnet: Deep learning on point sets for 3d classification and segmentation. In CVPR. 652--660.
[26]
Charles R Qi, Li Yi, Hao Su, and Leonidas J Guibas. 2017. PointNet: deep hierarchical feature learning on point sets in a metric space. In NeurIPS. 5105--5114.
[27]
Yossi Rubner, Carlo Tomasi, and Leonidas J Guibas. 2000. The earth mover's distance as a metric for image retrieval. IJCV, Vol. 40 (2000), 99--121.
[28]
Weijing Shi and Raj Rajkumar. 2020. Point-gnn: Graph neural network for 3d object detection in a point cloud. In CVPR. 1711--1719.
[29]
Yuliang Sun, Yongwei Miao, Jiazhou Chen, and Renato Pajarola. 2020. PGCNet: patch graph convolutional network for point cloud segmentation of indoor scenes. The Visual Computer, Vol. 36, 10 (2020), 2407--2418.
[30]
Abdel Aziz Taha and Allan Hanbury. 2015. Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC medical imaging, Vol. 15, 1 (2015), 1--28.
[31]
Keke Tang, Yuhong Chen, Weilong Peng, Yanling Zhang, Meie Fang, Zheng Wang, and Peng Song. 2023. Reppvconv: attentively fusing reparameterized voxel features for efficient 3d point cloud perception. The Visual Computer, Vol. 39, 11 (2023), 5577--5588.
[32]
Keke Tang, Xu He, Weilong Peng, Jianpeng Wu, Yawen Shi, Daizong Liu, Pan Zhou, Wenping Wang, and Zhihong Tian. 2024. Manifold Constraints for Imperceptible Adversarial Attacks on Point Clouds. In AAAI, Vol. 38. 5127--5135.
[33]
Keke Tang, Lujie Huang, Weilong Peng, Daizong Liu, Xiaofei Wang, Yang Ma, Ligang Liu, and Zhihong Tian. 2024. FLAT: Flux-aware Imperceptible Adversarial Attacks on 3D Point Clouds. In ECCV.
[34]
Keke Tang, Tianrui Lou, Weilong Peng, Nenglun Chen, Yawen Shi, and Wenping Wang. 2024. Effective Single-Step Adversarial Training With Energy-Based Models. IEEE TETCI (2024). https://doi.org/10.1109/TETCI.2024.3378652
[35]
Keke Tang, Yuexin Ma, Dingruibo Miao, Peng Song, Zhaoquan Gu, Zhihong Tian, and Wenping Wang. 2022. Decision fusion networks for image classification. IEEE TNNLS (2022). https://doi.org/10.1109/TNNLS.2022.3196129
[36]
Keke Tang, Jianpeng Wu, Weilong Peng, Yawen Shi, Peng Song, Zhaoquan Gu, Zhihong Tian, and Wenping Wang. 2023. Deep Manifold Attack on Point Clouds via Parameter Plane Stretching. In AAAI, Vol. 37. 2420--2428.
[37]
Hugues Thomas, Charles R Qi, Jean-Emmanuel Deschaud, Beatriz Marcotegui, Franccois Goulette, and Leonidas J Guibas. 2019. Kpconv: Flexible and deformable convolution for point clouds. In ICCV. 6411--6420.
[38]
T Vetter, T Poggio, and HH Bülthoff. 1994. The importance of symmetry and virtual views in three-dimensional object recognition. Current Biology, Vol. 4, 1 (1994), 18--23.
[39]
Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E Sarma, Michael M Bronstein, and Justin M Solomon. 2019. Dynamic graph cnn for learning on point clouds. ACM TOG (SIGGRAPH), Vol. 38, 5, Article 146 (2019), 12 pages.
[40]
Yuxin Wen, Jiehong Lin, Ke Chen, CL Philip Chen, and Kui Jia. 2020. Geometry-aware generation of adversarial point clouds. IEEE TPAMI, Vol. 44, 6 (2020), 2984--2999.
[41]
Matthew Wicker and Marta Kwiatkowska. 2019. Robustness of 3d deep learning in an adversarial setting. In CVPR. 11767--11775.
[42]
Wenxuan Wu, Zhongang Qi, and Li Fuxin. 2019. Pointconv: Deep convolutional networks on 3d point clouds. In CVPR. 9621--9630.
[43]
Ziyi Wu, Yueqi Duan, He Wang, Qingnan Fan, and Leonidas J Guibas. 2020. If-defense: 3d adversarial point cloud defense via implicit function based restoration. arXiv preprint arXiv:2010.05272 (2020).
[44]
Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 2015. 3d shapenets: A deep representation for volumetric shapes. In CVPR. 1912--1920.
[45]
Chong Xiang, Charles R. Qi, and Bo Li. 2019. Generating 3D Adversarial Point Clouds. In CVPR. 9136--9144.
[46]
Mutian Xu, Runyu Ding, Hengshuang Zhao, and Xiaojuan Qi. 2021. PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds. CVPR (2021).
[47]
Li Yi, Vladimir G Kim, Duygu Ceylan, I-Chao Shen, Mengyan Yan, Hao Su, Cewu Lu, Qixing Huang, Alla Sheffer, and Leonidas Guibas. 2016. A scalable active framework for region annotation in 3d shape collections. ACM Transactions on Graphics, Vol. 35, 6 (2016), 1--12.
[48]
Yusuke Yoshiyasu, Eiichi Yoshida, Kazuhito Yokoi, and Ryusuke Sagawa. 2014. Symmetry-aware nonrigid matching of incomplete 3d surfaces. In CVPR. 4193--4200.
[49]
Jing Yuan, Wu Qiu, Eranga Ukwatta, Martin Rajchl, Xue-Cheng Tai, and Aaron Fenster. 2013. Efficient 3D endfiring TRUS prostate segmentation with globally optimized rotational symmetry. In CVPR. 2211--2218.
[50]
Jingyu Zhang, Chunhua Jiang, Xupeng Wang, and Mumuxin Cai. 2021. Td-Net: Topology Destruction Network For Generating Adversarial Point Cloud. In ICIP. 3098--3102.
[51]
Renrui Zhang, Ziyu Guo, Peng Gao, Rongyao Fang, Bin Zhao, Dong Wang, Yu Qiao, and Hongsheng Li. 2022. Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training. arXiv preprint arXiv:2205.14401 (2022).
[52]
Hengshuang Zhao, Li Jiang, Chi-Wing Fu, and Jiaya Jia. 2019. Pointweb: Enhancing local neighborhood features for point cloud processing. In CVPR. 5565--5573.
[53]
Heng Zhao, Shenxing Wei, Dahu Shi, Wenming Tan, Zheyang Li, Ye Ren, Xing Wei, Yi Yang, and Shiliang Pu. 2023. Learning symmetry-aware geometry correspondences for 6D object pose estimation. In ICCV. 14045--14054.
[54]
Yue Zhao, Yuwei Wu, Caihua Chen, and Andrew Lim. 2020. On isometry robustness of deep 3d point cloud models under adversarial attacks. In CVPR. 1201--1210.
[55]
Tianhang Zheng, Changyou Chen, Junsong Yuan, Bo Li, and Kui Ren. 2019. Pointcloud saliency maps. In ICCV. 1598--1606.
[56]
Hang Zhou, Dongdong Chen, Jing Liao, Kejiang Chen, Xiaoyi Dong, Kunlin Liu, Weiming Zhang, Gang Hua, and Nenghai Yu. 2020. Lg-gan: Label guided adversarial network for flexible targeted attack of point cloud based deep networks. In CVPR. 10356--10365.
[57]
Hang Zhou, Kejiang Chen, Weiming Zhang, Han Fang, Wenbo Zhou, and Nenghai Yu. 2019. Dup-net: Denoiser and upsampler network for 3d adversarial point clouds defense. In ICCV. 1961--1970.
[58]
Peican Zhu, Zepeng Fan, Sensen Guo, Keke Tang, and Xingyu Li. 2024. Improving adversarial transferability through hybrid augmentation. Computers & Security, Vol. 139 (2024), 103674.
[59]
Peican Zhu, Jinbang Hong, Xingyu Li, Keke Tang, and Zhen Wang. 2023. SGMA: a novel adversarial attack approach with improved transferability. Complex & Intelligent Systems, Vol. 9, 5 (2023), 6051--6063.
Index Terms
- SymAttack: Symmetry-aware Imperceptible Adversarial Attacks on 3D Point Clouds
Recommendations
FLAT: Flux-Aware Imperceptible Adversarial Attacks on 3D Point Clouds
Computer Vision – ECCV 2024AbstractAdversarial attacks on point clouds play a vital role in assessing and enhancing the adversarial robustness of 3D deep learning models. While employing a variety of geometric constraints, existing adversarial attack solutions often display ...
Adversarial Shape Perturbations on 3D Point Clouds
Computer Vision – ECCV 2020 WorkshopsAbstractThe importance of training robust neural network grows as 3D data is increasingly utilized in deep learning for vision tasks in robotics, drone control, and autonomous driving. One commonly used 3D data type is 3D point clouds, which describe ...
Symmetry Defense Against CNN Adversarial Perturbation Attacks
Information SecurityAbstractThis paper uses symmetry to make Convolutional Neural Network classifiers (CNNs) robust against adversarial perturbation attacks. Such attacks add perturbation to original images to generate adversarial images that fool classifiers such as road ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
October 2024
11719 pages
ISBN:9798400706868
DOI:10.1145/3664647
- General Chairs:
- Jianfei Cai,
- Mohan Kankanhalli,
- Balakrishnan Prabhakaran,
- Susanne Boll,
- Program Chairs:
- Ramanathan Subramanian,
- Liang Zheng,
- Vivek K. Singh,
- Pablo Cesar,
- Lexing Xie,
- Dong Xu
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 28 October 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- Guangdong Basic and Applied Basic Research Foundation
- National Natural Science Foundation of China
- Academician Binxing Fang?s Specialized Class
- Guangzhou Sci-Tech Program
Conference
MM '24
Sponsor:
MM '24: The 32nd ACM International Conference on Multimedia
October 28 - November 1, 2024
Melbourne VIC, Australia
Acceptance Rates
MM '24 Paper Acceptance Rate 1,150 of 4,385 submissions, 26%;
Overall Acceptance Rate 2,145 of 8,556 submissions, 25%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 21Total Downloads
- Downloads (Last 12 months)21
- Downloads (Last 6 weeks)21
Reflects downloads up to 12 Nov 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in