# Adversarial Learning of Privacy-Preserving Text Representations for De-Identification of Medical Records

arXiv: https://arxiv.org/abs/1906.05000 · HTML: https://mlsanity.com/paper/1906.05000/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2019.

## Built on by (most cited first, 11 of 11)

- [CAPE: Context-Aware Private Embeddings for Private Language Learning](https://mlsanity.com/paper/2108.12318/) (2021)
- [How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processing](https://mlsanity.com/paper/2205.10095/) (2022)
- [De-identification of Privacy-related Entities in Job Postings](https://mlsanity.com/paper/2105.11223/) (2021)
- [Differential Privacy in Natural Language Processing: The Story So Far](https://mlsanity.com/paper/2208.08140/) (2022)
- [Unsupervised Text Deidentification](https://mlsanity.com/paper/2210.11528/) (2022)
- [Unlocking the Potential of Large Language Models for Clinical Text Anonymization: A Comparative Study](https://mlsanity.com/paper/2406.00062/) (2024)
- [Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts](https://mlsanity.com/paper/2204.04775/) (2022)
- [How Much User Context Do We Need? Privacy by Design in Mental Health NLP Application](https://mlsanity.com/paper/2209.02022/) (2022)
- [Paradox of De-identification: A Critique of HIPAA Safe Harbour in the Age of LLMs](https://mlsanity.com/paper/2602.08997/) (2026)
- [Token-Level Privacy in Large Language Models](https://mlsanity.com/paper/2503.03652/) (2025)
- [Private Vertical Federated Inference for Time-Series](https://mlsanity.com/paper/2605.08343/) (2026)

## Abstract (arXiv)

De-identification is the task of detecting protected health information (PHI) in medical text. It is a critical step in sanitizing electronic health records (EHRs) to be shared for research. Automatic de-identification classifierscan significantly speed up the sanitization process. However, obtaining a large and diverse dataset to train such a classifier that works wellacross many types of medical text poses a challenge as privacy laws prohibit the sharing of raw medical records. We introduce a method to create privacy-preserving shareable representations of medical text (i.e. they contain no PHI) that does not require expensive manual pseudonymization. These representations can be shared between organizations to create unified datasets for training de-identification models. Our representation allows training a simple LSTM-CRF de-identification model to an F1 score of 97.4%, which is comparable to a strong baseline that exposes private information in its representation. A robust, widely available de-identification classifier based on our representation could potentially enable studies for which de-identification would otherwise be too costly.