让3D点云数据无法被训练，仅授权用户可恢复使用。
Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need
- 按类别分配不同变换，使数据难以学习
- 在6个数据集上验证，16种模型均有效
- 适合保护敏感3D数据的科研与工业应用
传统不可学习策略多针对2D图像数据，而随着含敏感信息的3D点云数据增多，其未经授权的使用问题日益严重。为此，本文提出首个完整的3D点云不可学习框架，包含两部分：(i) 不可学习数据保护方案，通过类别自适应分配策略和样本级多变换实现；(ii) 数据恢复方案，利用类别级逆矩阵变换，仅允许授权用户恢复训练。该恢复机制是现有研究中常被忽略的实际问题——即使授权用户也难以从不可学习数据中获取知识。理论与实证结果（涵盖6个数据集、16个模型、2项任务）证明了该框架的有效性。代码已开源。
原文摘要 · Abstract (English)
Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data. With more 3D point cloud data containing sensitivity information, unauthorized usage of this new type data has also become a serious concern. To address this, we propose the first integral unlearnable framework for 3D point clouds including two processes: (i) we propose an unlearnable data protection scheme, involving a class-wise setting established by a category-adaptive allocation strategy and multi-transformations assigned to samples; (ii) we propose a data restoration scheme that utilizes class-wise inverse matrix transformation, thus enabling authorized-only training for unlearnable data. This restoration process is a practical issue overlooked in most existing unlearnable literature, \ie, even authorized users struggle to gain knowledge from 3D unlearnable data. Both theoretical and empirical results (including 6 datasets, 16 models, and 2 tasks) demonstrate the effectiveness of our proposed unlearnable framework. Our code is available at \url{https://github.com/CGCL-codes/UnlearnablePC}
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。