{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deflecting-3d-adversarial-point-clouds","title":"DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense","arxiv_id":"1812.11017","date":"2018-12-25","proceeding":"ICCV 2019 10","authors":["Hang Zhou","Kejiang Chen","Weiming Zhang","Han Fang","Wenbo Zhou","Nenghai Yu"],"abstract":"Neural networks are vulnerable to adversarial examples, which poses a threat to their application in security sensitive systems. We propose a Denoiser and UPsampler Network (DUP-Net) structure as defenses for 3D adversarial point cloud classification, where the two modules reconstruct surface smoothness by dropping or adding points. In this paper, statistical outlier removal (SOR) and a data-driven upsampling network are considered as denoiser and upsampler respectively. Compared with baseline defenses, DUP-Net has three advantages. First, with DUP-Net as a defense, the target model is more robust to white-box adversarial attacks. Second, the statistical outlier removal provides added robustness since it is a non-differentiable denoising operation. Third, the upsampler network can be trained on a small dataset and defends well against adversarial attacks generated from other point cloud datasets. We conduct various experiments to validate that DUP-Net is very effective as defense in practice. Our best defense eliminates 83.8% of C&W and l_2 loss based attack (point shifting), 50.0% of C&W and Hausdorff distance loss based attack (point adding) and 9.0% of saliency map based attack (point dropping) under 200 dropped points on PointNet.","url_abs":"https://arxiv.org/abs/1812.11017v2","url_pdf":"https://arxiv.org/pdf/1812.11017v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deflecting-3d-adversarial-point-clouds","repo_url":"https://github.com/RyanHangZhou/DUP-Net","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"point-cloud-classification","task_name":"Point Cloud Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.11017","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}