Score: 1

AuthenLoRA: Entangling Stylization with Imperceptible Watermarks for Copyright-Secure LoRA Adapters

Published: November 26, 2025 | arXiv ID: 2511.21216v1

By: Fangming Shi , Li Li , Kejiang Chen and more

Potential Business Impact:

Marks AI art so you know who made it.

Business Areas:
Identity Management Information Technology, Privacy and Security

Low-Rank Adaptation (LoRA) offers an efficient paradigm for customizing diffusion models, but its ease of redistribution raises concerns over unauthorized use and the generation of untraceable content. Existing watermarking techniques either target base models or verify LoRA modules themselves, yet they fail to propagate watermarks to generated images, leaving a critical gap in traceability. Moreover, traceability watermarking designed for base models is not tightly coupled with stylization and often introduces visual degradation or high false-positive detection rates. To address these limitations, we propose AuthenLoRA, a unified watermarking framework that embeds imperceptible, traceable watermarks directly into the LoRA training process while preserving stylization quality. AuthenLoRA employs a dual-objective optimization strategy that jointly learns the target style distribution and the watermark-induced distribution shift, ensuring that any image generated with the watermarked LoRA reliably carries the watermark. We further design an expanded LoRA architecture for enhanced multi-scale adaptation and introduce a zero-message regularization mechanism that substantially reduces false positives during watermark verification. Extensive experiments demonstrate that AuthenLoRA achieves high-fidelity stylization, robust watermark propagation, and significantly lower false-positive rates compared with existing approaches. Open-source implementation is available at: https://github.com/ShiFangming0823/AuthenLoRA

Country of Origin
🇨🇳 China

Repos / Data Links

Page Count
16 pages

Category
Computer Science:
Cryptography and Security