StealthMark: Harmless and stealthy ownership verification for medical segmentation via uncertainty-guided backdoors

Yu, Qinkai, Zhang, Chong, Jin, Gaojie, Huang, Tianjin, Zhou, Wei, Li, Wenhui, Jin, Xiaobo, Huang, Bo, Zhao, Yitian, Yang, Guang, Lip, Gregory Y.H., Zheng, Yalin, Villavicencio, Aline and Meng, Yanda 2026. StealthMark: Harmless and stealthy ownership verification for medical segmentation via uncertainty-guided backdoors. IEEE Transactions on Image Processing 35 , pp. 1290-1304. 10.1109/tip.2026.3655563

Full text not available from this repository.

Abstract

Annotating medical data for training AI models is often costly and limited due to the shortage of specialists with relevant clinical expertise. This challenge is further compounded by privacy and ethical concerns associated with sensitive patient information. As a result, well-trained medical segmentation models on private datasets constitute valuable intellectual property requiring robust protection mechanisms. Existing model protection techniques primarily focus on classification and generative tasks, while segmentation models—crucial to medical image analysis—remain largely underexplored. In this paper, we propose a novel, stealthy, and harmless method, StealthMark, for verifying the ownership of medical segmentation models under closed-box conditions. Our approach subtly modulates model uncertainty without altering the final segmentation outputs, thereby preserving the model’s performance. To enable ownership verification, we incorporate model-agnostic explanation methods, e.g. LIME, to extract feature attributions from the model outputs. Under specific triggering conditions, these explanations reveal a distinct and verifiable watermark. We further design the watermark as a QR code to facilitate robust and recognizable ownership claims. We conducted extensive experiments across four medical imaging datasets (CMR dataset from UK Biobank, the SEG fundus dataset, the EchoNet echocardiography dataset, and the PraNet colonoscopy dataset) and five mainstream segmentation models. The results demonstrate the effectiveness, stealthiness, and harmlessness of our method on the original model’s segmentation performance. For example, when applied to the SAM model, StealthMark consistently achieved attack success rates (ASR) above 95% across various datasets while maintaining less than a 1% drop in Dice and AUC scores—significantly outperforming backdoor-based watermarking methods and highlighting its strong potential for practical deployment. Our implementation code is made available at https://github.com/Qinkaiyu/StealthMark

Item Type:	Article
Date Type:	Published Online
Status:	Published
Schools:	Schools > Computer Science & Informatics
Additional Information:	License information from Publisher: LICENSE 1: URL: https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html, Start Date: 2026-01-01
Publisher:	Institute of Electrical and Electronics Engineers
ISSN:	1057-7149
Last Modified:	13 Feb 2026 12:00
URI:	https://orca.cardiff.ac.uk/id/eprint/184818

Actions (repository staff only)

Edit Item