AuthenLoRA_model

Official Model Repository for Paper AuthenLoRA: Entangling Stylization with Imperceptible Watermarks for Copyright-Secure LoRA Adapters

You can find the Pytorch implementation in Github and datasets in Huggingface

Method

<img src="fig/Threat_Model.png" alt="Alt" align="center" style="zoom:60%;" />

In this work, we propose AuthenLoRA, a novel watermarking method that effectively protects the copyright of LoRA models by embedding imperceptible watermarks during the generation of stylized images.

We jointly optimize style transfer and watermark embedding to achieve tight coupling between the two objectives. A lightweight mapper is introduced to modulate LoRA parameters, enabling dynamic modification of embedded watermarks without retraining. To suppress perceptual watermark residual and reduce false positives, we design the Perceptual Residual Tone Suppression (PRTS) loss and the Zero-Message Regularization strategy. Furthermore, we incorporate ResNet blocks into the fine-tuning scope, significantly improving training efficiency and watermark effectiveness.

We hope our work contributes to the advancement of digital asset copyright protection. :)

Visual Demonstration

<img src="fig/Visual_Results.png" alt="Alt" align="center" style="zoom:40%;" />