MIAD-MARK: Adversarial Watermarking of Medical Image for Protecting Copyright and Privacy

The rapid advancement of deep learning has significantly facilitated the integration of Artificial Intelligence (AI) into clinical practices. However, the frequent utilization of vast clinical data has raised concerns about copyright and patient privacy. Here, we introduce a framework that not only enables medical image copyright protection but also prevents unauthorized AI analysis. Specifically, we adhere to this framework and propose a novel visible adversarial watermark for medical images, MIAD-MARK, utilizing adaptable affine transforms to deceive unauthorized models. Furthermore, we enhance the robustness of MIAD-MARK to resist advanced watermark removal deep neural networks. Our approach involves linear variations, allowing for reversibility to recover the original images during the authorization process. We conduct experiments on various medical datasets, including different diseases and modalities. Our results demonstrate significant decreases in medical image foundation models and standard models. Our findings underscore that MIAD-MARK offers an effective, easily implemented, and robust solution to safeguard medical image copyright and patient privacy, thereby promoting the security of AI-driven medical image diagnosis in clinical applications.