©Plug-in Authorization for Human Content Copyright Protection in Text-to-Image Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Chao, Zhang, Huishuai, Bian, Jiang, Zhang, Weiming, Yu, Nenghai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915128544329728
author Zhou, Chao
Zhang, Huishuai
Bian, Jiang
Zhang, Weiming
Yu, Nenghai
author_facet Zhou, Chao
Zhang, Huishuai
Bian, Jiang
Zhang, Weiming
Yu, Nenghai
contents This paper addresses the contentious issue of copyright infringement in images generated by text-to-image models, sparking debates among AI developers, content creators, and legal entities. State-of-the-art models create high-quality content without crediting original creators, causing concern in the artistic community. To mitigate this, we propose the ©Plug-in Authorization framework, introducing three operations: addition, extraction, and combination. Addition involves training a ©plug-in for specific copyright, facilitating proper credit attribution. Extraction allows creators to reclaim copyright from infringing models, and combination enables users to merge different ©plug-ins. These operations act as permits, incentivizing fair use and providing flexibility in authorization. We present innovative approaches,"Reverse LoRA" for extraction and "EasyMerge" for seamless combination. Experiments in artist-style replication and cartoon IP recreation demonstrate ©plug-ins' effectiveness, offering a valuable solution for human copyright protection in the age of generative AIs. The code is available at https://github.com/zc1023/-Plug-in-Authorization.git.
format Preprint
id arxiv_https___arxiv_org_abs_2404_11962
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ©Plug-in Authorization for Human Content Copyright Protection in Text-to-Image Model
Zhou, Chao
Zhang, Huishuai
Bian, Jiang
Zhang, Weiming
Yu, Nenghai
Artificial Intelligence
Cryptography and Security
Computer Vision and Pattern Recognition
Machine Learning
This paper addresses the contentious issue of copyright infringement in images generated by text-to-image models, sparking debates among AI developers, content creators, and legal entities. State-of-the-art models create high-quality content without crediting original creators, causing concern in the artistic community. To mitigate this, we propose the ©Plug-in Authorization framework, introducing three operations: addition, extraction, and combination. Addition involves training a ©plug-in for specific copyright, facilitating proper credit attribution. Extraction allows creators to reclaim copyright from infringing models, and combination enables users to merge different ©plug-ins. These operations act as permits, incentivizing fair use and providing flexibility in authorization. We present innovative approaches,"Reverse LoRA" for extraction and "EasyMerge" for seamless combination. Experiments in artist-style replication and cartoon IP recreation demonstrate ©plug-ins' effectiveness, offering a valuable solution for human copyright protection in the age of generative AIs. The code is available at https://github.com/zc1023/-Plug-in-Authorization.git.
title ©Plug-in Authorization for Human Content Copyright Protection in Text-to-Image Model
topic Artificial Intelligence
Cryptography and Security
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2404.11962