AMIF: Authorizable Medical Image Fusion Model with Built-in Authentication

TL;DR

AMIF is a novel medical image fusion model that incorporates built-in authentication and authorization controls, protecting proprietary data and model integrity while enabling secure clinical application.

Contribution

This paper introduces AMIF, the first image fusion model with integrated authorization and visible copyright identifiers for secure medical imaging.

Findings

AMIF embeds visible copyright markers in fused images.

Authorized users can access high-quality fusion results via key-based authentication.

AMIF effectively prevents unauthorized inference and model reverse engineering.

Abstract

Multimodal image fusion enables precise lesion localization and characterization for accurate diagnosis, thereby strengthening clinical decision-making and driving its growing prominence in medical imaging research. A powerful multimodal image fusion model relies on high-quality, clinically representative multimodal training data and a rigorously engineered model architecture. Therefore, the development of such professional radiomics models represents a collaborative achievement grounded in standardized acquisition, clinical-specific expertise, and algorithmic design proficiency, which necessitates protection of associated intellectual property rights. However, current multimodal image fusion models generate fused outputs without built-in mechanisms to safeguard intellectual property rights, inadvertently exposing proprietary model knowledge and sensitive training data through inference leakage. For example, malicious users can exploit fusion outputs and model distillation or other inference-based reverse engineering techniques to approximate the fusion performance of proprietary models. To address this issue, we propose AMIF, the first Authorizable Medical Image Fusion model with built-in authentication, which integrates authorization access control into the image fusion objective. For unauthorized usage, AMIF embeds explicit and visible copyright identifiers into fusion results. In contrast, high-quality fusion results are accessible upon successful key-based authentication.