StealthMark: Harmless and Stealthy Ownership Verification for Medical Segmentation via Uncertainty-Guided Backdoors

2026-01-23

IEEE Transactions on Image Processing

AI Summary

This work proposes a novel, stealthy watermarking method for medical image segmentation models that simultaneously ensures imperceptibility, harmlessness, and black-box verifiability—capabilities lacking in existing ownership protection schemes. By leveraging uncertainty-guided backdoors, the approach modulates prediction uncertainty and integrates model-agnostic explanation techniques (e.g., LIME) to extract feature attributions, thereby embedding identifiable QR code watermarks without altering segmentation outputs. To the best of our knowledge, this is the first method to introduce harmless, covert watermarks into medical segmentation models, enabling efficient ownership verification in black-box settings. Extensive experiments across four medical datasets and five state-of-the-art models—including SAM—demonstrate over 95% watermark verification success rates, with negligible performance degradation (<1% drop in both Dice and AUC), significantly outperforming current backdoor-based watermarking approaches.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Graphical Models

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

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

Problem

• medical segmentation
• model ownership verification
• intellectual property protection
• stealthy watermarking
• black-box verification

Innovation

• uncertainty-guided backdoor
• model watermarking
• medical image segmentation
• black-box ownership verification
• explainability-based watermark