Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need

TL;DR

This paper introduces a novel unlearnable framework for 3D point clouds that protects data from unauthorized training while allowing authorized data restoration, validated through extensive experiments.

Contribution

It presents the first comprehensive unlearnable scheme for 3D point clouds, combining class-wise transformations with a restoration method for authorized use.

Findings

Effective data protection across 6 datasets

Successful data restoration for authorized users

Robustness demonstrated on 16 models and 2 tasks

Abstract

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}