# Masking Is Not Enough: Generative Restoration for Multimodal De-Identification in Medical AI

arXiv: https://arxiv.org/abs/2608.21133 · HTML: https://mlsanity.com/paper/2608.21133/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 29 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Builds on (most cited first, 14 of 14)

- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering](https://mlsanity.com/paper/2102.09542/) (2021)
- [Med-Flamingo: a Multimodal Medical Few-shot Learner](https://mlsanity.com/paper/2307.15189/) (2023)
- [Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review](https://mlsanity.com/paper/2403.02469/) (2024)
- [Patch-Based Image Inpainting with Generative Adversarial Networks](https://mlsanity.com/paper/1803.07422/) (2018)
- [De-Identification of Medical Imaging Data: A Comprehensive Tool for Ensuring Patient Privacy](https://mlsanity.com/paper/2410.12402/) (2024)
- [Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges](https://mlsanity.com/paper/2606.09125/) (2026)
- [From Redaction to Restoration: Deep Learning for Medical Image Anonymization and Reconstruction](https://mlsanity.com/paper/2604.11376/) (2026)

## Abstract (arXiv)

Medical image-text data can expose protected health information (PHI) through both visible image content as well as accompanying text, creating a barrier to privacy-preserving medical AI systems. This risk is especially prominent in multimodal systems, where images, questions, reports, and clinical context may enter training, evaluation, or inference pipelines. Existing medical vision-language benchmarks primarily emphasize task utility, while de-identification methods are often evaluated separately from downstream reasoning. We introduce ClinX, an end-to-end multimodal PHI sanitization framework for medical image-text data. ClinX detects visible identifiers with optical character recognition (OCR), constructs binary PHI masks, and applies ClinX-PRISM, a no-skip generative restoration module with privacy-oriented post-processing for burned-in identifier suppression. In parallel, text-side PHI is reduced through progressive de-identification levels: regex masking, context-aware masking, and rewrite-based sanitization. We evaluate ClinX in medical visual question answering (MedVQA), jointly measuring PHI leakage and downstream utility across image-side, text-side, and combined de-identification settings. Results show that OCR-only masking is not sufficient as a standalone solution, and restoration-based sanitization better preserves clinically relevant visual context while sharply reducing recoverable PHI.