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

2026-03-25

AI Summary

This work addresses the critical lack of built-in intellectual property (IP) protection in existing medical multimodal image fusion models, which are vulnerable to knowledge distillation and reverse engineering, risking both model theft and leakage of sensitive patient data. To this end, we propose AMIF, an authorization-enabled medical image fusion framework that uniquely integrates cryptographic key authentication, visible watermarking, and the fusion process into a unified pipeline. During inference, AMIF dynamically controls output quality: unauthorized users receive only low-fidelity fused images embedded with explicit copyright watermarks, while authorized users—upon successful key verification—obtain high-fidelity results. This approach effectively prevents unauthorized exploitation without compromising performance for legitimate users, establishing a novel paradigm for IP protection in medical imaging AI that jointly ensures security and image quality.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• medical image fusion
• intellectual property protection
• model authentication
• inference leakage
• multimodal imaging

Innovation

• Medical Image Fusion
• Model Authentication
• Intellectual Property Protection
• Authorization Control
• Inference Leakage Prevention