Semantic Deep Hiding for Robust Unlearnable Examples

TL;DR

This paper introduces a novel semantic deep hiding scheme using invertible neural networks to create robust unlearnable examples that resist common countermeasures, enhancing data privacy in deep learning.

Contribution

The paper proposes a new Deep Hiding scheme with a Latent Feature Concentration module and Semantic Images Generation module, improving robustness and high-level feature concealment of unlearnable examples.

Findings

Outperforms existing methods against 18 countermeasures.

Achieves high robustness on CIFAR-10, CIFAR-100, and ImageNet subset.

Effectively prevents unauthorized data exploitation.

Abstract

Ensuring data privacy and protection has become paramount in the era of deep learning. Unlearnable examples are proposed to mislead the deep learning models and prevent data from unauthorized exploration by adding small perturbations to data. However, such perturbations (e.g., noise, texture, color change) predominantly impact low-level features, making them vulnerable to common countermeasures. In contrast, semantic images with intricate shapes have a wealth of high-level features, making them more resilient to countermeasures and potential for producing robust unlearnable examples. In this paper, we propose a Deep Hiding (DH) scheme that adaptively hides semantic images enriched with high-level features. We employ an Invertible Neural Network (INN) to invisibly integrate predefined images, inherently hiding them with deceptive perturbations. To enhance data unlearnability, we introduce a Latent Feature Concentration module, designed to work with the INN, regularizing the intra-class variance of these perturbations. To further boost the robustness of unlearnable examples, we design a Semantic Images Generation module that produces hidden semantic images. By utilizing similar semantic information, this module generates similar semantic images for samples within the same classes, thereby enlarging the inter-class distance and narrowing the intra-class distance. Extensive experiments on CIFAR-10, CIFAR-100, and an ImageNet subset, against 18 countermeasures, reveal that our proposed method exhibits outstanding robustness for unlearnable examples, demonstrating its efficacy in preventing unauthorized data exploitation.