Protective Perturbations against Unauthorized Data Usage in Diffusion-based Image Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Peng, Sen, Yang, Jijia, Wang, Mingyue, He, Jianfei, Jia, Xiaohua
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916543277826048
author Peng, Sen
Yang, Jijia
Wang, Mingyue
He, Jianfei
Jia, Xiaohua
author_facet Peng, Sen
Yang, Jijia
Wang, Mingyue
He, Jianfei
Jia, Xiaohua
contents Diffusion-based text-to-image models have shown immense potential for various image-related tasks. However, despite their prominence and popularity, customizing these models using unauthorized data also brings serious privacy and intellectual property issues. Existing methods introduce protective perturbations based on adversarial attacks, which are applied to the customization samples. In this systematization of knowledge, we present a comprehensive survey of protective perturbation methods designed to prevent unauthorized data usage in diffusion-based image generation. We establish the threat model and categorize the downstream tasks relevant to these methods, providing a detailed analysis of their designs. We also propose a completed evaluation framework for these perturbation techniques, aiming to advance research in this field.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18791
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Protective Perturbations against Unauthorized Data Usage in Diffusion-based Image Generation
Peng, Sen
Yang, Jijia
Wang, Mingyue
He, Jianfei
Jia, Xiaohua
Computer Vision and Pattern Recognition
Diffusion-based text-to-image models have shown immense potential for various image-related tasks. However, despite their prominence and popularity, customizing these models using unauthorized data also brings serious privacy and intellectual property issues. Existing methods introduce protective perturbations based on adversarial attacks, which are applied to the customization samples. In this systematization of knowledge, we present a comprehensive survey of protective perturbation methods designed to prevent unauthorized data usage in diffusion-based image generation. We establish the threat model and categorize the downstream tasks relevant to these methods, providing a detailed analysis of their designs. We also propose a completed evaluation framework for these perturbation techniques, aiming to advance research in this field.
title Protective Perturbations against Unauthorized Data Usage in Diffusion-based Image Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.18791