EnTruth: Enhancing the Traceability of Unauthorized Dataset Usage in Text-to-image Diffusion Models with Minimal and Robust Alterations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ren, Jie, Cui, Yingqian, Chen, Chen, Xing, Yue, Liu, Hui, Lyu, Lingjuan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912729142394880
author Ren, Jie
Cui, Yingqian
Chen, Chen
Xing, Yue
Liu, Hui
Lyu, Lingjuan
author_facet Ren, Jie
Cui, Yingqian
Chen, Chen
Xing, Yue
Liu, Hui
Lyu, Lingjuan
contents Generative models, especially text-to-image diffusion models, have significantly advanced in their ability to generate images, benefiting from enhanced architectures, increased computational power, and large-scale datasets. While the datasets play an important role, their protection has remained as an unsolved issue. Current protection strategies, such as watermarks and membership inference, are either in high poison rate which is detrimental to image quality or suffer from low accuracy and robustness. In this work, we introduce a novel approach, EnTruth, which Enhances Traceability of unauthorized dataset usage utilizing template memorization. By strategically incorporating the template memorization, EnTruth can trigger the specific behavior in unauthorized models as the evidence of infringement. Our method is the first to investigate the positive application of memorization and use it for copyright protection, which turns a curse into a blessing and offers a pioneering perspective for unauthorized usage detection in generative models. Comprehensive experiments are provided to demonstrate its effectiveness in terms of data-alteration rate, accuracy, robustness and generation quality.
format Preprint
id arxiv_https___arxiv_org_abs_2406_13933
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EnTruth: Enhancing the Traceability of Unauthorized Dataset Usage in Text-to-image Diffusion Models with Minimal and Robust Alterations
Ren, Jie
Cui, Yingqian
Chen, Chen
Xing, Yue
Liu, Hui
Lyu, Lingjuan
Cryptography and Security
Generative models, especially text-to-image diffusion models, have significantly advanced in their ability to generate images, benefiting from enhanced architectures, increased computational power, and large-scale datasets. While the datasets play an important role, their protection has remained as an unsolved issue. Current protection strategies, such as watermarks and membership inference, are either in high poison rate which is detrimental to image quality or suffer from low accuracy and robustness. In this work, we introduce a novel approach, EnTruth, which Enhances Traceability of unauthorized dataset usage utilizing template memorization. By strategically incorporating the template memorization, EnTruth can trigger the specific behavior in unauthorized models as the evidence of infringement. Our method is the first to investigate the positive application of memorization and use it for copyright protection, which turns a curse into a blessing and offers a pioneering perspective for unauthorized usage detection in generative models. Comprehensive experiments are provided to demonstrate its effectiveness in terms of data-alteration rate, accuracy, robustness and generation quality.
title EnTruth: Enhancing the Traceability of Unauthorized Dataset Usage in Text-to-image Diffusion Models with Minimal and Robust Alterations
topic Cryptography and Security
url https://arxiv.org/abs/2406.13933