{"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/dynamics-aware-adversarial-attack-of-3d","title":"Dynamics-aware Adversarial Attack of 3D Sparse Convolution Network","arxiv_id":"2112.09428","date":"2021-12-17","proceeding":null,"authors":["An Tao","Yueqi Duan","He Wang","Ziyi Wu","Pengliang Ji","Haowen Sun","Jie zhou","Jiwen Lu"],"abstract":"In this paper, we investigate the dynamics-aware adversarial attack problem in deep neural networks. Most existing adversarial attack algorithms are designed under a basic assumption -- the network architecture is fixed throughout the attack process. However, this assumption does not hold for many recently proposed networks, e.g. 3D sparse convolution network, which contains input-dependent execution to improve computational efficiency. It results in a serious issue of lagged gradient, making the learned attack at the current step ineffective due to the architecture changes afterward. To address this issue, we propose a Leaded Gradient Method (LGM) and show the significant effects of the lagged gradient. More specifically, we re-formulate the gradients to be aware of the potential dynamic changes of network architectures, so that the learned attack better \"leads\" the next step than the dynamics-unaware methods when network architecture changes dynamically. Extensive experiments on various datasets show that our LGM achieves impressive performance on semantic segmentation and classification. Compared with the dynamic-unaware methods, LGM achieves about 20% lower mIoU averagely on the ScanNet and S3DIS datasets. LGM also outperforms the recent point cloud attacks.","url_abs":"https://arxiv.org/abs/2112.09428v2","url_pdf":"https://arxiv.org/pdf/2112.09428v2.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":"dynamics-aware-adversarial-attack-of-3d","repo_url":"https://github.com/AnTao97/LGM","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-classification","task_name":"3D Classification"},{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"}],"methods":[{"method_slug":"aware","method_name":"AWARE"},{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}