Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Survey (2307.00309v2)

Published 1 Jul 2023 in cs.CV, cs.LG, and eess.IV

Abstract: Deep learning has successfully solved a wide range of tasks in 2D vision as a dominant AI technique. Recently, deep learning on 3D point clouds is becoming increasingly popular for addressing various tasks in this field. Despite remarkable achievements, deep learning algorithms are vulnerable to adversarial attacks. These attacks are imperceptible to the human eye but can easily fool deep neural networks in the testing and deployment stage. To encourage future research, this survey summarizes the current progress on adversarial attack and defense techniques on point cloud classification.This paper first introduces the principles and characteristics of adversarial attacks and summarizes and analyzes adversarial example generation methods in recent years. Additionally, it provides an overview of defense strategies, organized into data-focused and model-focused methods. Finally, it presents several current challenges and potential future research directions in this domain.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (148)
  1. Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015.
  2. Y. Li, “Research and application of deep learning in image recognition,” in IEEE International Conference on Power, Electronics and Computer Applications (ICPECA).   IEEE, 2022, pp. 994–999.
  3. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” Communications of the ACM, vol. 60, no. 6, pp. 84–90, 2017.
  4. H. Naderi, L. Goli, and S. Kasaei, “Scale equivariant cnns with scale steerable filters,” in International Conference on Machine Vision and Image Processing (MVIP).   IEEE, 2020, pp. 1–5.
  5. N. Silberman and R. Fergus, “Indoor scene segmentation using a structured light sensor,” in Proc. IEEE/CVF ICCV workshops.   IEEE, 2011, pp. 601–608.
  6. Y. Mo, Y. Wu, X. Yang, F. Liu, and Y. Liao, “Review the state-of-the-art technologies of semantic segmentation based on deep learning,” Neurocomputing, vol. 493, pp. 626–646, 2022.
  7. A. B. Nassif, I. Shahin, I. Attili, M. Azzeh, and K. Shaalan, “Speech recognition using deep neural networks: A systematic review,” IEEE Access, vol. 7, pp. 19 143–19 165, 2019.
  8. K. I. Taher and A. M. Abdulazeez, “Deep learning convolutional neural network for speech recognition: a review,” International Journal of Science and Business, vol. 5, no. 3, pp. 1–14, 2021.
  9. K. Chowdhary, “Natural language processing,” Fundamentals of Artificial Intelligence, pp. 603–649, 2020.
  10. C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus, “Intriguing properties of neural networks,” in Proc. ICLR, 2014.
  11. S.-M. Moosavi-Dezfooli, A. Fawzi, and P. Frossard, “Deepfool: a simple and accurate method to fool deep neural networks,” in Proc. IEEE/CVF CVPR, 2016, pp. 2574–2582.
  12. K. Eykholt, I. Evtimov, E. Fernandes, B. Li, A. Rahmati, C. Xiao, A. Prakash, T. Kohno, and D. Song, “Robust physical-world attacks on deep learning visual classification,” in Proc. IEEE/CVF CVPR, 2018, pp. 1625–1634.
  13. M. Mozaffari-Kermani, S. Sur-Kolay, A. Raghunathan, and N. K. Jha, “Systematic poisoning attacks on and defenses for machine learning in healthcare,” IEEE Journal of Biomedical and Health Informatics, vol. 19, no. 6, pp. 1893–1905, 2014.
  14. C. Badue, R. Guidolini, R. V. Carneiro, P. Azevedo, V. B. Cardoso, A. Forechi, L. Jesus, R. Berriel, T. M. Paixao, F. Mutz et al., “Self-driving cars: A survey,” Expert Systems with Applications, vol. 165, p. 113816, 2021.
  15. M. Hassanalian and A. Abdelkefi, “Classifications, applications, and design challenges of drones: A review,” Progress in Aerospace Sciences, vol. 91, pp. 99–131, 2017.
  16. H. A. Pierson and M. S. Gashler, “Deep learning in robotics: a review of recent research,” Advanced Robotics, vol. 31, no. 16, pp. 821–835, 2017.
  17. Z. Liu, H. Tang, Y. Lin, and S. Han, “Point-voxel cnn for efficient 3d deep learning,” Advances in Neural Information Processing Systems, vol. 32, 2019.
  18. L. Ladicky, O. Saurer, S. Jeong, F. Maninchedda, and M. Pollefeys, “From point clouds to mesh using regression,” in Proc. IEEE/CVF ICCV, 2017, pp. 3893–3902.
  19. C. R. Qi, H. Su, K. Mo, and L. J. Guibas, “Pointnet: Deep learning on point sets for 3d classification and segmentation,” in Proc. IEEE/CVF CVPR, 2017, pp. 652–660.
  20. N. Akhtar and A. Mian, “Threat of adversarial attacks on deep learning in computer vision: A survey,” IEEE Access, vol. 6, pp. 14 410–14 430, 2018.
  21. X. Yuan, P. He, Q. Zhu, and X. Li, “Adversarial examples: Attacks and defenses for deep learning,” IEEE Trans. Neural Networks and Learning Systems, vol. 30, no. 9, pp. 2805–2824, 2019.
  22. S. Qiu, Q. Liu, S. Zhou, and C. Wu, “Review of artificial intelligence adversarial attack and defense technologies,” Applied Sciences, vol. 9, no. 5, p. 909, 2019.
  23. H. Wei, H. Tang, X. Jia, H. Yu, Z. Li, Z. Wang, S. Satoh, L. Van Gool, and Z. Wang, “Physical adversarial attack meets computer vision: A decade survey,” arXiv preprint arXiv:2209.15179, 2023.
  24. Z. Zhai, P. Li, and S. Feng, “State of the art on adversarial attacks and defenses in graphs,” Neural Computing and Applications, pp. 1–22, 2023.
  25. P. Bountakas, A. Zarras, A. Lekidis, and C. Xenakis, “Defense strategies for adversarial machine learning: A survey,” Computer Science Review, vol. 49, p. 100573, 2023.
  26. S. Pavlitska, N. Lambing, and J. M. Zöllner, “Adversarial attacks on traffic sign recognition: A survey,” in International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME).   IEEE, 2023, pp. 1–6.
  27. N. Akhtar, A. Mian, N. Kardan, and M. Shah, “Advances in adversarial attacks and defenses in computer vision: A survey,” IEEE Access, vol. 9, pp. 155 161–155 196, 2021.
  28. Y. Guo, H. Wang, Q. Hu, H. Liu, L. Liu, and M. Bennamoun, “Deep learning for 3d point clouds: A survey,” IEEE Trans. PAMI, 2020.
  29. A. Xiao, J. Huang, D. Guan, X. Zhang, S. Lu, and L. Shao, “Unsupervised point cloud representation learning with deep neural networks: A survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
  30. Y. Xie, J. Tian, and X. X. Zhu, “Linking points with labels in 3d: A review of point cloud semantic segmentation,” IEEE Geoscience and remote sensing magazine, vol. 8, no. 4, pp. 38–59, 2020.
  31. H. Zhang, C. Wang, S. Tian, B. Lu, L. Zhang, X. Ning, and X. Bai, “Deep learning-based 3d point cloud classification: A systematic survey and outlook,” Displays, p. 102456, 2023.
  32. D. Fernandes, A. Silva, R. Névoa, C. Simões, D. Gonzalez, M. Guevara, P. Novais, J. Monteiro, and P. Melo-Pinto, “Point-cloud based 3d object detection and classification methods for self-driving applications: A survey and taxonomy,” Information Fusion, vol. 68, pp. 161–191, 2021.
  33. D. Krawczyk and R. Sitnik, “Segmentation of 3d point cloud data representing full human body geometry: A review,” Pattern Recognition, p. 109444, 2023.
  34. C. Cao, M. Preda, and T. Zaharia, “3d point cloud compression: A survey,” in The 24th International Conference on 3D Web Technology, 2019, pp. 1–9.
  35. R. R. Wiyatno, A. Xu, O. Dia, and A. de Berker, “Adversarial examples in modern machine learning: A review,” arXiv preprint arXiv:1911.05268, 2019.
  36. H. Xu, Y. Ma, H.-C. Liu, D. Deb, H. Liu, J.-L. Tang, and A. K. Jain, “Adversarial attacks and defenses in images, graphs and text: A review,” International Journal of Automation and Computing, vol. 17, pp. 151–178, 2020.
  37. N. Martins, J. M. Cruz, T. Cruz, and P. H. Abreu, “Adversarial machine learning applied to intrusion and malware scenarios: a systematic review,” IEEE Access, vol. 8, pp. 35 403–35 419, 2020.
  38. A. Chakraborty, M. Alam, V. Dey, A. Chattopadhyay, and D. Mukhopadhyay, “A survey on adversarial attacks and defences,” CAAI Transactions on Intelligence Technology, vol. 6, no. 1, pp. 25–45, 2021.
  39. I. Rosenberg, A. Shabtai, Y. Elovici, and L. Rokach, “Adversarial machine learning attacks and defense methods in the cyber security domain,” ACM Computing Surveys (CSUR), vol. 54, no. 5, pp. 1–36, 2021.
  40. A. Michel, S. K. Jha, and R. Ewetz, “A survey on the vulnerability of deep neural networks against adversarial attacks,” Progress in Artificial Intelligence, pp. 1–11, 2022.
  41. H. Tan, L. Wang, H. Zhang, J. Zhang, M. Shafiq, and Z. Gu, “Adversarial attack and defense strategies of speaker recognition systems: A survey,” Electronics, vol. 11, no. 14, p. 2183, 2022.
  42. S. Qiu, Q. Liu, S. Zhou, and W. Huang, “Adversarial attack and defense technologies in natural language processing: A survey,” Neurocomputing, vol. 492, pp. 278–307, 2022.
  43. H. Liang, E. He, Y. Zhao, Z. Jia, and H. Li, “Adversarial attack and defense: A survey,” Electronics, vol. 11, no. 8, p. 1283, 2022.
  44. Y. Li, M. Cheng, C.-J. Hsieh, and T. C. Lee, “A review of adversarial attack and defense for classification methods,” The American Statistician, pp. 1–17, 2022.
  45. K. D. Gupta and D. Dasgupta, “Adversarial attacks and defenses for deployed ai models,” IT Professional, vol. 24, no. 4, pp. 37–41, 2022.
  46. X. Wei, B. Pu, J. Lu, and B. Wu, “Physically adversarial attacks and defenses in computer vision: A survey,” arXiv preprint arXiv:2211.01671, 2022.
  47. J.-X. Mi, X.-D. Wang, L.-F. Zhou, and K. Cheng, “Adversarial examples based on object detection tasks: A survey,” Neurocomputing, 2022.
  48. S. Y. Khamaiseh, D. Bagagem, A. Al-Alaj, M. Mancino, and H. W. Alomari, “Adversarial deep learning: A survey on adversarial attacks and defense mechanisms on image classification,” IEEE Access, 2022.
  49. S. Kotyan, “A reading survey on adversarial machine learning: Adversarial attacks and their understanding,” arXiv preprint arXiv:2308.03363, 2023.
  50. H. Baniecki and P. Biecek, “Adversarial attacks and defenses in explainable artificial intelligence: A survey,” in Proc. ICML Workshop AdvML-Frontiers, 2023.
  51. S. Han, C. Lin, C. Shen, Q. Wang, and X. Guan, “Interpreting adversarial examples in deep learning: A review,” ACM Computing Surveys, 2023.
  52. D. Tian, H. Ochimizu, C. Feng, R. Cohen, and A. Vetro, “Geometric distortion metrics for point cloud compression,” in Proc. IEEE ICIP, 2017, pp. 3460–3464.
  53. C. Xiang, C. R. Qi, and B. Li, “Generating 3d adversarial point clouds,” in Proc. IEEE/CVF CVPR, 2019, pp. 9136–9144.
  54. T. Zheng, C. Chen, J. Yuan, B. Li, and K. Ren, “Pointcloud saliency maps,” in Proc. IEEE/CVF ICCV, 2019, pp. 1598–1606.
  55. A. Hamdi, S. Rojas, A. Thabet, and B. Ghanem, “Advpc: Transferable adversarial perturbations on 3d point clouds,” in Computer Vision – ECCV.   Springer, 2020, pp. 241–257.
  56. K. Lee, Z. Chen, X. Yan, R. Urtasun, and E. Yumer, “Shapeadv: Generating shape-aware adversarial 3d point clouds,” arXiv preprint arXiv:2005.11626, 2020.
  57. H. Zhou, D. Chen, J. Liao, K. Chen, X. Dong, K. Liu, W. Zhang, G. Hua, and N. Yu, “Lg-gan: Label guided adversarial network for flexible targeted attack of point cloud based deep networks,” in Proc. IEEE/CVF CVPR, 2020, pp. 10 356–10 365.
  58. Y. Wen, J. Lin, K. Chen, C. P. Chen, and K. Jia, “Geometry-aware generation of adversarial point clouds,” IEEE Trans. PAMI, 2020.
  59. T. Tsai, K. Yang, T.-Y. Ho, and Y. Jin, “Robust adversarial objects against deep learning models,” in Proc. AAAI Conf. Artif. Intell, vol. 34, no. 01, 2020, pp. 954–962.
  60. D. Liu, R. Yu, and H. Su, “Extending adversarial attacks and defenses to deep 3D point cloud classifiers,” in IEEE International Conference on Image Processing (ICIP).   IEEE, 2019, pp. 2279–2283.
  61. A. Arya, H. Naderi, and S. Kasaei, “Adversarial attack by limited point cloud surface modifications,” in International Conference on Pattern Recognition and Image Analysis (IPRIA).   IEEE, 2023, pp. 1–8.
  62. D. Liu, R. Yu, and H. Su, “Adversarial shape perturbations on 3d point clouds,” in Computer Vision – ECCV.   Springer, 2020, pp. 88–104.
  63. J. Kim, B.-S. Hua, T. Nguyen, and S.-K. Yeung, “Minimal adversarial examples for deep learning on 3d point clouds,” in Proc. IEEE/CVF ICCV, 2021, pp. 7797–7806.
  64. C. Ma, W. Meng, B. Wu, S. Xu, and X. Zhang, “Efficient joint gradient based attack against sor defense for 3d point cloud classification,” in Proc. ACM International Conference on Multimedia, 2020, pp. 1819–1827.
  65. D. Liu and W. Hu, “Imperceptible transfer attack and defense on 3d point cloud classification,” IEEE Trans. PAMI, 2022.
  66. J. Yang, Q. Zhang, R. Fang, B. Ni, J. Liu, and Q. Tian, “Adversarial attack and defense on point sets,” arXiv preprint arXiv:1902.10899, 2019.
  67. M. Wicker and M. Kwiatkowska, “Robustness of 3d deep learning in an adversarial setting,” in Proc. IEEE/CVF CVPR, 2019, pp. 11 767–11 775.
  68. B. He, J. Liu, Y. Li, S. Liang, J. Li, X. Jia, and X. Cao, “Generating transferable 3d adversarial point cloud via random perturbation factorization,” in Proc. AAAI Conf. Artif. Intell, vol. 37, no. 1, 2023, pp. 764–772.
  69. I. J. Goodfellow, J. Shlens, and C. Szegedy, “Explaining and harnessing adversarial examples,” in Proc. ICLR, 2015.
  70. Y. Dong, F. Liao, T. Pang, H. Su, J. Zhu, X. Hu, and J. Li, “Boosting adversarial attacks with momentum,” in Proc. IEEE/CVF CVPR, 2018, pp. 9185–9193.
  71. A. M\kadry, A. Makelov, L. Schmidt, D. Tsipras, and A. Vladu, “Towards deep learning models resistant to adversarial attacks,” STAT, vol. 1050, p. 9, 2017.
  72. N. Carlini and D. Wagner, “Towards evaluating the robustness of neural networks,” in IEEE Symposium on Security and Privacy (SP).   IEEE, 2017, pp. 39–57.
  73. J. Zhang, L. Chen, B. Liu, B. Ouyang, Q. Xie, J. Zhu, W. Li, and Y. Meng, “3d adversarial attacks beyond point cloud,” Information Sciences, vol. 633, pp. 491–503, 2023.
  74. B. Liu, J. Zhang, and J. Zhu, “Boosting 3d adversarial attacks with attacking on frequency,” IEEE Access, vol. 10, pp. 50 974–50 984, 2022.
  75. D. I. Shuman, S. K. Narang, P. Frossard, A. Ortega, and P. Vandergheynst, “The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains,” IEEE Signal Processing Magazine, vol. 30, no. 3, pp. 83–98, 2013.
  76. D. Liu, W. Hu, and X. Li, “Point cloud attacks in graph spectral domain: When 3d geometry meets graph signal processing,” arXiv preprint arXiv:2207.13326, 2022.
  77. Q. Hu, D. Liu, and W. Hu, “Exploring the devil in graph spectral domain for 3d point cloud attacks,” in Computer Vision – ECCV.   Springer, 2022, pp. 229–248.
  78. Q. Huang, X. Dong, D. Chen, H. Zhou, W. Zhang, and N. Yu, “Shape-invariant 3d adversarial point clouds,” in Proc. IEEE/CVF CVPR, 2022, pp. 15 335–15 344.
  79. Y. Zhao, Y. Wu, C. Chen, and A. Lim, “On isometry robustness of deep 3d point cloud models under adversarial attacks,” in Proc. IEEE/CVF CVPR, 2020, pp. 1201–1210.
  80. D. Russo, B. Van Roy, A. K. Benjamin, and A. Osband, “A tutorial on thompson sampling. foundations and trends,” Machine Learning, vol. 11, no. 10.1561, p. 2200000070, 2017.
  81. K. Tang, Y. Shi, J. Wu, W. Peng, A. Khan, P. Zhu, and Z. Gu, “Normalattack: Curvature-aware shape deformation along normals for imperceptible point cloud attack,” Security and Communication Networks, vol. 2022, 2022.
  82. Y. Zhao, I. Shumailov, R. Mullins, and R. Anderson, “Nudge attacks on point-cloud dnns,” arXiv preprint arXiv:2011.11637, 2020.
  83. J. Su, D. V. Vargas, and K. Sakurai, “One pixel attack for fooling deep neural networks,” IEEE Trans. Evolutionary Computation, vol. 23, no. 5, pp. 828–841, 2019.
  84. H. Tan and H. Kotthaus, “Explainability-aware one point attack for point cloud neural networks,” in Proc. IEEE/CVF WACV, 2023, pp. 4581–4590.
  85. Z. Shi, C. Zhi, X. Zhenbo, Y. Wei, Y. Zhidong, and L. Huang, “Shape prior guided attack: Sparser perturbations on 3d point clouds,” in Proc. AAAI Conf. Artif. Intell, 2022.
  86. B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba, “Learning deep features for discriminative localization,” in Proc. IEEE/CVF CVPR, 2016, pp. 2921–2929.
  87. H. Naderi, C. Dinesh, I. V. Bajić, and S. Kasaei, “Model-free prediction of adversarial drop points in 3D point clouds,” arXiv preprint arXiv:2210.14164, 2022.
  88. K. Tang, J. Wu, W. Peng, Y. Shi, P. Song, Z. Gu, Z. Tian, and W. Wang, “Deep manifold attack on point clouds via parameter plane stretching,” in Proc. AAAI Conf. Artif. Intell, vol. 37, no. 2, 2023, pp. 2420–2428.
  89. X. Dai, Y. Li, H. Dai, and B. Xiao, “Generating unrestricted 3d adversarial point clouds,” arXiv preprint arXiv:2111.08973, 2021.
  90. T. B. Brown, N. Carlini, C. Zhang, C. Olsson, P. Christiano, and I. Goodfellow, “Unrestricted adversarial examples,” arXiv preprint arXiv:1809.08352, 2018.
  91. H. Naderi, L. Goli, and S. Kasaei, “Generating unrestricted adversarial examples via three parameters,” Multimedia Tools and Applications, vol. -, no. -, pp. –, 2022.
  92. Y. Song, R. Shu, N. Kushman, and S. Ermon, “Constructing unrestricted adversarial examples with generative models,” Advances in Neural Information Processing Systems, vol. 31, 2018.
  93. I. Lang, U. Kotlicki, and S. Avidan, “Geometric adversarial attacks and defenses on 3d point clouds,” in International Conference on 3D Vision (3DV).   IEEE, 2021, pp. 1196–1205.
  94. G. Mariani, L. Cosmo, A. M. Bronstein, and E. Rodola, “Generating adversarial surfaces via band-limited perturbations,” in Computer Graphics Forum, vol. 39, no. 5.   Wiley Online Library, 2020, pp. 253–264.
  95. B. S. Vivek, K. R. Mopuri, and R. V. Babu, “Gray-box adversarial training,” in Proc. ECCV, Sept. 2018, pp. 203–218.
  96. X. Dong, D. Chen, H. Zhou, G. Hua, W. Zhang, and N. Yu, “Self-robust 3d point recognition via gather-vector guidance,” in Proc. IEEE/CVF CVPR.   IEEE, 2020, pp. 11 513–11 521.
  97. I. Lang, U. Kotlicki, and S. Avidan, “Geometric adversarial attacks and defenses on 3D point clouds,” in Proc. Int. Conf. 3D Vision (3DV), 2021, pp. 1196–1205.
  98. Z. Wu, Y. Duan, H. Wang, Q. Fan, and L. J. Guibas, “If-defense: 3d adversarial point cloud defense via implicit function based restoration,” arXiv preprint arXiv:2010.05272, 2020.
  99. H. Naderi, K. Noorbakhsh, A. Etemadi, and S. Kasaei, “Lpf-defense: 3d adversarial defense based on frequency analysis,” Plos One, vol. 18, no. 2, p. e0271388, 2023.
  100. H. Zhou, K. Chen, W. Zhang, H. Fang, W. Zhou, and N. Yu, “Dup-net: Denoiser and upsampler network for 3d adversarial point clouds defense,” in Proc. IEEE/CVF ICCV, 2019, pp. 1961–1970.
  101. Q. Liang, Q. Li, W. Nie, and A.-A. Liu, “Pagn: perturbation adaption generation network for point cloud adversarial defense,” Multimedia Systems, pp. 1–9, 2022.
  102. J. Sun, Y. Cao, C. B. Choy, Z. Yu, A. Anandkumar, Z. M. Mao, and C. Xiao, “Adversarially robust 3d point cloud recognition using self-supervisions,” Advances in Neural Information Processing Systems, vol. 34, 2021.
  103. Y. Zhang, J. Hou, and Y. Yuan, “A comprehensive study and comparison of the robustness of 3d object detectors against adversarial attacks,” arXiv preprint arXiv:2212.10230, 2022.
  104. J. Zhang, L. Chen, B. Ouyang, B. Liu, J. Zhu, Y. Chen, Y. Meng, and D. Wu, “Pointcutmix: Regularization strategy for point cloud classification,” Neurocomputing, vol. 505, pp. 58–67, 2022.
  105. Y. Zhang, G. Liang, T. Salem, and N. Jacobs, “Defense-PointNet: Protecting pointnet against adversarial attacks,” in IEEE International Conference on Big Data.   IEEE, 2019, pp. 5654–5660.
  106. K. Li, Z. Zhang, C. Zhong, and G. Wang, “Robust structured declarative classifiers for 3d point clouds: Defending adversarial attacks with implicit gradients,” in Proc. IEEE/CVF CVPR, 2022, pp. 15 294–15 304.
  107. J. Sun, K. Koenig, Y. Cao, Q. A. Chen, and Z. Mao, “On the adversarial robustness of 3d point cloud classification,” in Proc. BMVC, 2021.
  108. H. Zhou, K. Chen, W. Zhang, H. Fang, W. Zhou, and N. Yu, “Deflecting 3d adversarial point clouds through outlier-guided removal,” arXiv preprint arXiv:1812.11017, 2018.
  109. L. Yu, X. Li, C.-W. Fu, D. Cohen-Or, and P.-A. Heng, “Pu-net: Point cloud upsampling network,” in Proc. IEEE/CVF CVPR, 2018, pp. 2790–2799.
  110. S. Peng, M. Niemeyer, L. Mescheder, M. Pollefeys, and A. Geiger, “Convolutional occupancy networks,” in Computer Vision – ECCV.   Springer, 2020, pp. 523–540.
  111. L. Mescheder, M. Oechsle, M. Niemeyer, S. Nowozin, and A. Geiger, “Occupancy networks: Learning 3d reconstruction in function space,” in Proc. IEEE/CVF CVPR, 2019, pp. 4460–4470.
  112. K. Zhang, H. Zhou, J. Zhang, Q. Huang, W. Zhang, and N. Yu, “Ada3diff: Defending against 3D adversarial point clouds via adaptive diffusion,” in Proc. ACM Multimedia, 2023, pp. 8849–8859.
  113. H. Liu, J. Jia, and N. Z. Gong, “Pointguard: Provably robust 3d point cloud classification,” in Proc. IEEE/CVF CVPR, 2021, pp. 6186–6195.
  114. T. S. Cohen, M. Geiger, J. Köhler, and M. Welling, “Spherical CNNs,” in Proc. ICLR, 2018.
  115. G. Li, G. Xu, H. Qiu, R. He, J. Li, and T. Zhang, “Improving adversarial robustness of 3D point cloud classification models,” in Computer Vision – ECCV.   Springer, 2022, pp. 672–689.
  116. Y. Wang, Y. Sun, Z. Liu, S. E. Sarma, M. M. Bronstein, and J. M. Solomon, “Dynamic graph CNN for learning on point clouds,” ACM Trans. Graphics, vol. 38, no. 5, pp. 1–12, 2019.
  117. M. Kiefel, V. Jampani, and P. V. Gehler, “Permutohedral lattice cnns,” arXiv preprint arXiv:1412.6618, 2015.
  118. Z. Wu, S. Song, A. Khosla, F. Yu, L. Zhang, X. Tang, and J. Xiao, “3d shapenets: A deep representation for volumetric shapes,” in Proc. IEEE/CVF CVPR, 2015, pp. 1912–1920.
  119. A. X. Chang, T. Funkhouser, L. Guibas, P. Hanrahan, Q. Huang, Z. Li, S. Savarese, M. Savva, S. Song, H. Su et al., “Shapenet: An information-rich 3d model repository,” arXiv preprint arXiv:1512.03012, 2015.
  120. M. A. Uy, Q.-H. Pham, B.-S. Hua, T. Nguyen, and S.-K. Yeung, “Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data,” in Proc. IEEE/CVF ICCV, 2019, pp. 1588–1597.
  121. K. Siddiqi, J. Zhang, D. Macrini, A. Shokoufandeh, S. Bouix, and S. Dickinson, “Retrieving articulated 3-d models using medial surfaces,” Machine Vision and Applications, vol. 19, no. 4, pp. 261–275, 2008.
  122. A. Dai, A. X. Chang, M. Savva, M. Halber, T. Funkhouser, and M. Nießner, “Scannet: Richly-annotated 3d reconstructions of indoor scenes,” in Proc. IEEE/CVF CVPR, 2017, pp. 5828–5839.
  123. M. De Deuge, A. Quadros, C. Hung, and B. Douillard, “Unsupervised feature learning for classification of outdoor 3d scans,” in Australasian Conference on Robitics and Automation, vol. 2.   University of New South Wales Kensington, Australia, 2013, p. 1.
  124. A. Gaidon, Q. Wang, Y. Cabon, and E. Vig, “Virtual worlds as proxy for multi-object tracking analysis,” in Proc. IEEE/CVF CVPR, 2016, pp. 4340–4349.
  125. A. Geiger, P. Lenz, and R. Urtasun, “Are we ready for autonomous driving? the kitti vision benchmark suite,” in Proc. IEEE/CVF CVPR.   IEEE, 2012, pp. 3354–3361.
  126. C. Dinesh, I. V. Bajić, and G. Cheung, “Adaptive nonrigid inpainting of three-dimensional point cloud geometry,” IEEE Signal Processing Letters, vol. 25, no. 6, pp. 878–882, 2018.
  127. C. Dinesh, G. Cheung, and I. V. Bajić, “Point cloud denoising via feature graph laplacian regularization,” IEEE Trans. Image Processing, vol. 29, pp. 4143–4158, 2020.
  128. “A 3d version of the mnist database of handwritten digits,” https://www.kaggle.com/datasets/daavoo/3d-mnist, accessed: 2019-01-30.
  129. J. Sun, Y. Cao, C. Choy, Z. Yu, C. Xiao, A. Anandkumar, and Z. M. Mao, “Improving adversarial robustness in 3d point cloud classification via self-supervisions,” in International Conference on Machine Learning Workshop (ICMLW), vol. 1, 2021.
  130. K. Tang, Y. Shi, T. Lou, W. Peng, X. He, P. Zhu, Z. Gu, and Z. Tian, “Rethinking perturbation directions for imperceptible adversarial attacks on point clouds,” IEEE Internet of Things Journal, 2022.
  131. D. D. Denipitiyage, T. Ajanthan, P. Kamalaruban, and A. Weller, “Provable defense against clustering attacks on 3d point clouds,” in AAAI-22 Workshop on Adversarial Machine Learning and Beyond, 2021.
  132. Y. Sun, F. Chen, Z. Chen, and M. Wang, “Local aggressive adversarial attacks on 3d point cloud,” in Asian Conference on Machine Learning.   PMLR, 2021, pp. 65–80.
  133. C. Ma, W. Meng, B. Wu, S. Xu, and X. Zhang, “Towards effective adversarial attack against 3d point cloud classification,” in Proc. IEEE ICME, 2021.
  134. Y. Dong, J. Zhu, X.-S. Gao et al., “Isometric 3d adversarial examples in the physical world,” Advances in Neural Information Processing Systems (NeurIPS), vol. 35, pp. 19 716–19 731, 2022.
  135. F. He, Y. Chen, R. Chen, and W. Nie, “Point cloud adversarial perturbation generation for adversarial attacks,” IEEE Access, vol. 11, pp. 2767–2774, 2023.
  136. R. Cheng, N. Sang, Y. Zhou, and X. Wang, “Universal adversarial attack against 3d object tracking,” in IEEE 23rd Int Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys).   IEEE, 2021, pp. 34–40.
  137. C. R. Qi, L. Yi, H. Su, and L. J. Guibas, “Pointnet++: Deep hierarchical feature learning on point sets in a metric space,” Advances in Neural Information Processing Systems, vol. 30, 2017.
  138. A. V. Phan, M. Le Nguyen, Y. L. H. Nguyen, and L. T. Bui, “Dgcnn: A convolutional neural network over large-scale labeled graphs,” Neural Networks, vol. 108, pp. 533–543, 2018.
  139. W. Wu, Z. Qi, and L. Fuxin, “Pointconv: Deep convolutional networks on 3d point clouds,” in Proc. IEEE/CVF CVPR, 2019, pp. 9621–9630.
  140. Y. Liu, B. Fan, S. Xiang, and C. Pan, “Relation-shape convolutional neural network for point cloud analysis,” in Proc. IEEE/CVF CVPR, 2019, pp. 8895–8904.
  141. D. Maturana and S. Scherer, “Voxnet: A 3d convolutional neural network for real-time object recognition,” in 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).   IEEE, 2015, pp. 922–928.
  142. Y. Xu, T. Fan, M. Xu, L. Zeng, and Y. Qiao, “Spidercnn: Deep learning on point sets with parameterized convolutional filters,” in Computer Vision – ECCV, 2018, pp. 87–102.
  143. X. Yan, C. Zheng, Z. Li, S. Wang, and S. Cui, “Pointasnl: Robust point clouds processing using nonlocal neural networks with adaptive sampling,” in Proc. IEEE/CVF CVPR, 2020, pp. 5589–5598.
  144. T. Xiang, C. Zhang, Y. Song, J. Yu, and W. Cai, “Walk in the cloud: Learning curves for point clouds shape analysis,” in Proc. IEEE/CVF ICCV, 2021, pp. 915–924.
  145. T. Groueix, M. Fisher, V. G. Kim, B. C. Russell, and M. Aubry, “A papier-mâché approach to learning 3d surface generation,” in Proc. IEEE/CVF CVPR, 2018, pp. 216–224.
  146. H. Zhao, L. Jiang, J. Jia, P. H. Torr, and V. Koltun, “Point transformer,” in Proc. IEEE/CVF ICCV, 2021, pp. 16 259–16 268.
  147. X. Ma, C. Qin, H. You, H. Ran, and Y. Fu, “Rethinking network design and local geometry in point cloud: A simple residual mlp framework,” in Proc. ICLR, 2022.
  148. E. d’Eon, B. Harrison, T. Myers, and P. A. Chou, “8i voxelized full bodies - a voxelized point cloud dataset,” ISO/IEC JTC1/SC29 Joint WG11/WG1 (MPEG / JPEG) input document WG11M40059/WG1M74006, Jan. 2017, http://plenodb.jpeg.org/pc/8ilabs/.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now