Hide Identity, Preserve Pathology: Diffusion-Based Anonymization for Chest X-rays

Yasmeena Akhter, Muskan Dosi, Mayank Vatsa, Richa Singh
Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare, PMLR 317:27-36, 2026.

Abstract

Chest X-rays are a widely-used, cost-effective imaging modality for medical investigations; however, they encode distinctive biometric signatures that enable identification attacks. We introduce PrivDiff-Net, a novel diffusion-based framework that addresses critical privacy vulnerabilities in chest X-rays through anatomical biometric features while preserving essential diagnostic utility for clinical applications. Our approach introduces two modules in a latent diffusion framework: (1) a Selective Attribute Suppression (SAS) module that removes sensitive identity cues using orthogonal projection in cross-attention, and (2) a Selective Privacy Guidance (SPG) loss that discourages identity features while preserving diagnostic information during diffusion. Quantitative results show that PrivDiff-Net achieves near-random identification (AUC: 47%) while maintaining high diagnostic accuracy (AUC: 78%). It effectively suppresses sensitive attributes and produces high-quality anonymized CXRs, validated by clinicians for diagnostic utility. These results establish PrivDiff-Net as a new benchmark for privacy-preserving Chest X-rays, providing a practical solution for secure data sharing in collaborative research environments while enabling ethical deployment of AI systems in healthcare where transparency and patient privacy are critical.

Cite this Paper

BibTeX
@InProceedings{pmlr-v317-akhter26a, title = {Hide Identity, Preserve Pathology: Diffusion-Based Anonymization for Chest X-rays}, author = {Akhter, Yasmeena and Dosi, Muskan and Vatsa, Mayank and Singh, Richa}, booktitle = {Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare}, pages = {27--36}, year = {2026}, editor = {Wu, Junde and Pan, Jiazhen and Zhu, Jiayuan and Luo, Luyang and Li, Yitong and Xu, Min and Jin, Yueming and Rueckert, Daniel}, volume = {317}, series = {Proceedings of Machine Learning Research}, month = {20--21 Jan}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v317/main/assets/akhter26a/akhter26a.pdf}, url = {https://proceedings.mlr.press/v317/akhter26a.html}, abstract = {Chest X-rays are a widely-used, cost-effective imaging modality for medical investigations; however, they encode distinctive biometric signatures that enable identification attacks. We introduce PrivDiff-Net, a novel diffusion-based framework that addresses critical privacy vulnerabilities in chest X-rays through anatomical biometric features while preserving essential diagnostic utility for clinical applications. Our approach introduces two modules in a latent diffusion framework: (1) a Selective Attribute Suppression (SAS) module that removes sensitive identity cues using orthogonal projection in cross-attention, and (2) a Selective Privacy Guidance (SPG) loss that discourages identity features while preserving diagnostic information during diffusion. Quantitative results show that PrivDiff-Net achieves near-random identification (AUC: 47%) while maintaining high diagnostic accuracy (AUC: 78%). It effectively suppresses sensitive attributes and produces high-quality anonymized CXRs, validated by clinicians for diagnostic utility. These results establish PrivDiff-Net as a new benchmark for privacy-preserving Chest X-rays, providing a practical solution for secure data sharing in collaborative research environments while enabling ethical deployment of AI systems in healthcare where transparency and patient privacy are critical.} }
Endnote
%0 Conference Paper %T Hide Identity, Preserve Pathology: Diffusion-Based Anonymization for Chest X-rays %A Yasmeena Akhter %A Muskan Dosi %A Mayank Vatsa %A Richa Singh %B Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare %C Proceedings of Machine Learning Research %D 2026 %E Junde Wu %E Jiazhen Pan %E Jiayuan Zhu %E Luyang Luo %E Yitong Li %E Min Xu %E Yueming Jin %E Daniel Rueckert %F pmlr-v317-akhter26a %I PMLR %P 27--36 %U https://proceedings.mlr.press/v317/akhter26a.html %V 317 %X Chest X-rays are a widely-used, cost-effective imaging modality for medical investigations; however, they encode distinctive biometric signatures that enable identification attacks. We introduce PrivDiff-Net, a novel diffusion-based framework that addresses critical privacy vulnerabilities in chest X-rays through anatomical biometric features while preserving essential diagnostic utility for clinical applications. Our approach introduces two modules in a latent diffusion framework: (1) a Selective Attribute Suppression (SAS) module that removes sensitive identity cues using orthogonal projection in cross-attention, and (2) a Selective Privacy Guidance (SPG) loss that discourages identity features while preserving diagnostic information during diffusion. Quantitative results show that PrivDiff-Net achieves near-random identification (AUC: 47%) while maintaining high diagnostic accuracy (AUC: 78%). It effectively suppresses sensitive attributes and produces high-quality anonymized CXRs, validated by clinicians for diagnostic utility. These results establish PrivDiff-Net as a new benchmark for privacy-preserving Chest X-rays, providing a practical solution for secure data sharing in collaborative research environments while enabling ethical deployment of AI systems in healthcare where transparency and patient privacy are critical.
APA
Akhter, Y., Dosi, M., Vatsa, M. & Singh, R.. (2026). Hide Identity, Preserve Pathology: Diffusion-Based Anonymization for Chest X-rays. Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare, in Proceedings of Machine Learning Research 317:27-36 Available from https://proceedings.mlr.press/v317/akhter26a.html.

Related Material