# I Am Not What I Write: Privacy Preserving Text Representation Learning

arXiv: https://arxiv.org/abs/1907.03189 · HTML: https://mlsanity.com/paper/1907.03189/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2019.

## Built on by (most cited first, 12 of 12)

- [Differentially Private Language Models for Secure Data Sharing](https://mlsanity.com/paper/2210.13918/) (2022)
- [CAPE: Context-Aware Private Embeddings for Private Language Learning](https://mlsanity.com/paper/2108.12318/) (2021)
- [Unlearning Protected User Attributes in Recommendations with Adversarial Training](https://mlsanity.com/paper/2206.04500/) (2022)
- [You Are What You Write: Preserving Privacy in the Era of Large Language Models](https://mlsanity.com/paper/2204.09391/) (2022)
- [How reparametrization trick broke differentially-private text representation learning](https://mlsanity.com/paper/2202.12138/) (2022)
- [1-Diffractor: Efficient and Utility-Preserving Text Obfuscation Leveraging Word-Level Metric Differential Privacy](https://mlsanity.com/paper/2405.01678/) (2024)
- [Exposing Privacy Risks in Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.17222/) (2025)
- [A Neighbourhood-Aware Differential Privacy Mechanism for Static Word Embeddings](https://mlsanity.com/paper/2309.10551/) (2023)
- [On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey](https://mlsanity.com/paper/2507.20783/) (2025)
- [How Much User Context Do We Need? Privacy by Design in Mental Health NLP Application](https://mlsanity.com/paper/2209.02022/) (2022)
- [Investigating User Perspectives on Differentially Private Text Privatization](https://mlsanity.com/paper/2503.09338/) (2025)
- [PrivBench: A Holistic and Modular Benchmarking Platform for Evaluating Text-to-Text Privatization](https://mlsanity.com/paper/2608.29624/) (2026)

## Abstract (arXiv)

Online users generate tremendous amounts of textual information by participating in different activities, such as writing reviews and sharing tweets. This textual data provides opportunities for researchers and business partners to study and understand individuals. However, this user-generated textual data not only can reveal the identity of the user but also may contain individual's private information (e.g., age, location, gender). Hence, "you are what you write" as the saying goes. Publishing the textual data thus compromises the privacy of individuals who provided it. The need arises for data publishers to protect people's privacy by anonymizing the data before publishing it. It is challenging to design effective anonymization techniques for textual information which minimizes the chances of re-identification and does not contain users' sensitive information (high privacy) while retaining the semantic meaning of the data for given tasks (high utility). In this paper, we study this problem and propose a novel double privacy preserving text representation learning framework, DPText, which learns a textual representation that (1) is differentially private, (2) does not contain private information and (3) retains high utility for the given task. Evaluating on two natural language processing tasks, i.e., sentiment analysis and part of speech tagging, we show the effectiveness of this approach in terms of preserving both privacy and utility.