{"type":"ScholarlyArticle","title":"Toward LoRA Copyright Protection with an Authorized Dual-Watermarking Framework","authors":[{"name":"Zhipeng Yin","slug":"zhipeng-yin","given":"Zhipeng","family":"Yin","affiliation":""},{"name":"Zichong Wang","slug":"zichong-wang","given":"Zichong","family":"Wang","affiliation":""},{"name":"Ruijun Chen","slug":"ruijun-chen","given":"Ruijun","family":"Chen","affiliation":""},{"name":"Xin Ning","slug":"xin-ning","given":"Xin","family":"Ning","affiliation":""},{"name":"Xingyu Zhang","slug":"xingyu-zhang","given":"Xingyu","family":"Zhang","affiliation":""},{"name":"Wenbin Zhang","slug":"wenbin-zhang","given":"Wenbin","family":"Zhang","affiliation":""}],"abstract":"Text-to-Image (T2I) diffusion models have been widely adopted due to their strong generative capabilities, while Low-Rank Adaptation (LoRA) has emerged as an efficient mechanism for customizing these models for diverse creative and commercial applications. This trend has fostered LoRA-centric service platforms that that enable the customization and commercial distribution of LoRA modules according to user requirements. However, the growing prevalence of LoRA and its critical role in customized AI services have raised urgent concerns about LoRA copyright protection. To address this gap, we propose LoRA2D, an authorized dual-watermarking framework specifically designed to protect LoRA modules in T2I diffusion models. LoRA2D integrates license-based authorization control with explicit watermarks as visible deterrents for unauthorized or trial usage, which can be removed upon valid authorization, while persistently embedding an implicit watermark for robust black-box ownership verification. Extensive experiments on multiple image-generation datasets demonstrate the effectiveness and practicality of LoRA2D for securing copyrights in LoRA-adapted T2I diffusion models.","doi":"10.24963/ijcai.2026/96","url":"https://ijcai.org/proceedings/2026/96","pdf":"https://ijcai.org/proceedings/2026/0096.pdf","markdown":"https://ijcai.org/proceedings/2026/96.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/96","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"AI Ethics, Trust, Fairnes","track":"Main Track","number":96,"pages":{"first":853,"last":861},"keywords":["AI Ethics, Trust, Fairnes: AI and law, governance, regulation","AI Ethics, Trust, Fairnes: Societal impact of AI","AI Ethics, Trust, Fairnes: Ethical, legal and societal issues","AI Ethics, Trust, Fairnes: Trustworthy AI"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}