paper-with-me

홈 › Papers

Semantic Deep Hiding for Robust Unlearnable Examples

2024-06-25 · Ruohan Meng, Chenyu Yi, Yi Yu, Siyuan Yang, Bingquan Shen, Alex C. Kot

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.

📄 PDF Abstract BibTeX arXiv:2406.17349

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms

2026-04-18 · Bo Wang, Jia Ni, Mengnan Zhao, Zhan Qin 외 arxiv

The unauthorized use of personal data in model training has emerged as a growing privacy threat. Unlearnable examples (UEs) address this issue by embedding imperceptible perturbations into benign examples to obstruct fea…

Detection and Defense of Unlearnable Examples

2023-12-14 · Yifan Zhu, Lijia Yu, Xiao-Shan Gao

Privacy preserving has become increasingly critical with the emergence of social media. Unlearnable examples have been proposed to avoid leaking personal information on the Internet by degrading generalization abilities …

Adversarial DefensePrivacy Preserving

Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information

2026-03-04 · Yifan Zhu, Yibo Miao, Yinpeng Dong, Xiao-Shan Gao arxiv

The volume of freely scraped data on the Internet has driven the tremendous success of deep learning. Along with this comes the growing concern about data privacy and security. Numerous methods for generating unlearnable…

UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation

2024-10-13 · Ye Sun, Hao Zhang, Tiehua Zhang, Xingjun Ma 외

Image segmentation is a crucial vision task that groups pixels within an image into semantically meaningful segments, which is pivotal in obtaining a fine-grained understanding of real-world scenes. However, an increasin…

AllBilevel OptimizationImage SegmentationInteractive Segmentation+2

How Far Are We from True Unlearnability?

2025-09-09 · Kai Ye, Liangcai Su, Chenxiong Qian arxiv

High-quality data plays an indispensable role in the era of large models, but the use of unauthorized data for model training greatly damages the interests of data owners. To overcome this threat, several unlearnable met…

Representation LearningSemantic Segmentation