Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples

TL;DR

This paper introduces Unlearnable Clusters, a novel method for creating label-agnostic unlearnable examples using cluster-wise perturbations and VLPMs, enhancing data protection against diverse exploitation scenarios.

Contribution

It proposes a new label-agnostic unlearnable example generation technique called Unlearnable Clusters, leveraging VLPMs for better transferability across different models and domains.

Findings

Effective in preventing unauthorized model training across various datasets.

Outperforms existing methods in label-agnostic settings.

Works on commercial platforms like Azure and Baidu PaddlePaddle.

Abstract

There is a growing interest in developing unlearnable examples (UEs) against visual privacy leaks on the Internet. UEs are training samples added with invisible but unlearnable noise, which have been found can prevent unauthorized training of machine learning models. UEs typically are generated via a bilevel optimization framework with a surrogate model to remove (minimize) errors from the original samples, and then applied to protect the data against unknown target models. However, existing UE generation methods all rely on an ideal assumption called label-consistency, where the hackers and protectors are assumed to hold the same label for a given sample. In this work, we propose and promote a more practical label-agnostic setting, where the hackers may exploit the protected data quite differently from the protectors. E.g., a m-class unlearnable dataset held by the protector may be exploited by the hacker as a n-class dataset. Existing UE generation methods are rendered ineffective in this challenging setting. To tackle this challenge, we present a novel technique called Unlearnable Clusters (UCs) to generate label-agnostic unlearnable examples with cluster-wise perturbations. Furthermore, we propose to leverage VisionandLanguage Pre-trained Models (VLPMs) like CLIP as the surrogate model to improve the transferability of the crafted UCs to diverse domains. We empirically verify the effectiveness of our proposed approach under a variety of settings with different datasets, target models, and even commercial platforms Microsoft Azure and Baidu PaddlePaddle. Code is available at \url{https://github.com/jiamingzhang94/Unlearnable-Clusters}.