The Latens Patronus: Seamless Model Watermarking for Latent Diffusion Model in IoT Environments

With the rapid development of the Internet of Things (IoT), generative artificial intelligence has been widely applied in various IoT applications. However, the wide adoption of the latent diffusion model (LDM) in such IoT scenarios raises severe risks of copyright infringement and model theft due to the lack of effective protection mechanisms. To address this challenge, we propose Latens Patronus, a seamless model watermarking technique for copyright protection of LDM in IoT environments. Unlike existing model watermarking methods, our method does not require additional watermark input and additional parameters for a specialized embedding network, making it more suitable for deployment in real-world IoT applications. Specifically, we design a watermark encoder (WME) to integrate an image watermark into latent features during the generation process and a watermark decoder (WMD) to accordingly extract the watermark from suspicious images accurately. We further introduce a diminishing training strategy that gradually fades out auxiliary supervision signals, eliminating the need for persistent watermark guidance and adding no extra overhead to the original model. Extensive experiments on multiple LDM variants demonstrate that Latens Patronus outperforms existing watermarking methods in both invisibility and robustness against image-level and model-level attacks.