X-Mark: Saliency-Guided Robust Dataset Ownership Verification for Medical Imaging

2026-02-10

AI Summary

This work addresses the copyright and ethical concerns arising from unauthorized use of high-quality medical images, a challenge exacerbated by the incompatibility of existing watermarking techniques with the stringent requirements of medical imaging—namely high resolution, dynamic scale variation, and preservation of diagnostic fidelity. To this end, we propose X-Mark, a sample-specific clean-label watermarking method tailored for chest X-ray images. X-Mark uniquely integrates saliency-guided perturbation with a scale-invariant watermarking mechanism, leveraging a conditional U-Net to inject imperceptible perturbations into diagnostically salient regions. Laplacian regularization is introduced to suppress high-frequency noise, while multi-objective training ensures both diagnostic accuracy and watermark robustness. Evaluated on the CheXpert dataset, X-Mark achieves 100% watermarking success, reduces false positive rates by 12% under the Ind-M setting, and demonstrates strong resilience against diverse adaptive attacks.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Adversarial Learning & Robustness
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Responsible Web: Algorithmic accountability and transparency on the web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

High-quality medical imaging datasets are essential for training deep learning models, but their unauthorized use raises serious copyright and ethical concerns. Medical imaging presents a unique challenge for existing dataset ownership verification methods designed for natural images, as static watermark patterns generated in fixed-scale images scale poorly dynamic and high-resolution scans with limited visual diversity and subtle anatomical structures, while preserving diagnostic quality. In this paper, we propose X-Mark, a sample-specific clean-label watermarking method for chest x-ray copyright protection. Specifically, X-Mark uses a conditional U-Net to generate unique perturbations within salient regions of each sample. We design a multi-component training objective to ensure watermark efficacy, robustness against dynamic scaling processes while preserving diagnostic quality and visual-distinguishability. We incorporate Laplacian regularization into our training objective to penalize high-frequency perturbations and achieve watermark scale-invariance. Ownership verification is performed in a black-box setting to detect characteristic behaviors in suspicious models. Extensive experiments on CheXpert verify the effectiveness of X-Mark, achieving WSR of 100% and reducing probability of false positives in Ind-M scenario by 12%, while demonstrating resistance to potential adaptive attacks.

Problem

• dataset ownership verification
• medical imaging
• watermarking
• copyright protection
• scale-invariance

Innovation

• saliency-guided watermarking
• conditional U-Net
• scale-invariant perturbation
• medical image copyright protection
• black-box ownership verification