Logo image
Back
Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?
Conference proceeding   Open access

Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?

Zhengyue Zhao, Jinhao Duan, Kaidi Xu, Chenan Wang, Rui Zhang, Zidong Du, Qi Guo and Xing Hu
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 24398-24407
16 Jun 2024
DOI: https://doi.org/10.1109/CVPR52733.2024.02303
url
https://arxiv.org/abs/2312.00084View
SubmittedarXiv.org - Non-exclusive license to distribute,  Open

Abstract

adversarial examples copyright protection diffusion models Perturbation methods Privacy protective perturbation Technological innovation Threat modeling Transform coding Semantics Systematics
Stable Diffusion has established itself as a foundation model in generative AI artistic applications, receiving widespread research and application. Some recent fine-tuning methods have made it feasible for individuals to implant personalized concepts onto the basic Stable Diffusion model with minimal computational costs on small datasets. However, these innovations have also given rise to issues like facial privacy forgery and artistic copyright infringement. In recent studies, researchers have explored the addition of imperceptible adversarial perturbations to images to prevent potential unauthorized exploitation and infringements when personal data is used for fine-tuning Stable Dif-fusion. Although these studies have demonstrated the ability to protect images, it is essential to consider that these methods may not be entirely applicable in real-world scenarios. In this paper, we systematically evaluate the use of perturbations to protect images within a practical threat model. The results suggest that these approaches may not be sufficient to safeguard image privacy and copyright effectively. Furthermore, we introduce a purification method capable of removing protected perturbations while preserving the original image structure to the greatest extent possible. Experiments reveal that Stable Diffusion can effectively learn from purified images over all protective methods 1 .

Metrics

12 Record Views
2 citations in Scopus

Details

Logo image