Saved in:
Bibliographic Details
Main Authors: Song, Jie, Jia, Jun, Sun, Wei, Zhou, Wangqiu, Tan, Tao, Zhai, Guangtao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.24296
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917361537253376
author Song, Jie
Jia, Jun
Sun, Wei
Zhou, Wangqiu
Tan, Tao
Zhai, Guangtao
author_facet Song, Jie
Jia, Jun
Sun, Wei
Zhou, Wangqiu
Tan, Tao
Zhai, Guangtao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_24296
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AMIF: Authorizable Medical Image Fusion Model with Built-in Authentication
Song, Jie
Jia, Jun
Sun, Wei
Zhou, Wangqiu
Tan, Tao
Zhai, Guangtao
Computer Vision and Pattern Recognition
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.
title AMIF: Authorizable Medical Image Fusion Model with Built-in Authentication
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.24296