# ER-AE: Differentially Private Text Generation for Authorship Anonymization

arXiv: https://arxiv.org/abs/1907.08736 · HTML: https://mlsanity.com/paper/1907.08736/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jul 2019.

## Built on by (most cited first, 30 of 35)

- [Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe](https://mlsanity.com/paper/2210.14348/) (2022)
- [Differentially Private Language Models for Secure Data Sharing](https://mlsanity.com/paper/2210.13918/) (2022)
- [The Limits of Word Level Differential Privacy](https://mlsanity.com/paper/2205.02130/) (2022)
- [LLM-PBE: Assessing Data Privacy in Large Language Models](https://mlsanity.com/paper/2408.12787/) (2024)
- [SoK: Privacy-Preserving Data Synthesis](https://mlsanity.com/paper/2307.02106/) (2023)
- [DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewriting](https://mlsanity.com/paper/2208.10400/) (2022)
- [DP-BART for Privatized Text Rewriting under Local Differential Privacy](https://mlsanity.com/paper/2302.07636/) (2023)
- [PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration](https://mlsanity.com/paper/2406.01394/) (2024)
- [Differentially Private Natural Language Models: Recent Advances and Future Directions](https://mlsanity.com/paper/2301.09112/) (2023)
- [A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage](https://mlsanity.com/paper/2504.21035/) (2025)
- [Adversarial Stylometry in the Wild: Transferable Lexical Substitution Attacks on Author Profiling](https://mlsanity.com/paper/2101.11310/) (2021)
- [Differential Privacy in Natural Language Processing: The Story So Far](https://mlsanity.com/paper/2208.08140/) (2022)
- [1-Diffractor: Efficient and Utility-Preserving Text Obfuscation Leveraging Word-Level Metric Differential Privacy](https://mlsanity.com/paper/2405.01678/) (2024)
- [Keep It Private: Unsupervised Privatization of Online Text](https://mlsanity.com/paper/2405.10260/) (2024)
- [Just Rewrite It Again: A Post-Processing Method for Enhanced Semantic Similarity and Privacy Preservation of Differentially Private Rewritten Text](https://mlsanity.com/paper/2405.19831/) (2024)
- [NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human](https://mlsanity.com/paper/2406.03749/) (2024)
- [On the Impact of Noise in Differentially Private Text Rewriting](https://mlsanity.com/paper/2501.19022/) (2025)
- [From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey](https://mlsanity.com/paper/2110.15871/) (2021)
- [Spend Your Budget Wisely: Towards an Intelligent Distribution of the Privacy Budget in Differentially Private Text Rewriting](https://mlsanity.com/paper/2503.22379/) (2025)
- [Style Transfer with Multi-iteration Preference Optimization](https://mlsanity.com/paper/2406.11581/) (2024)
- [A Girl Has A Name, And It's ... Adversarial Authorship Attribution for Deobfuscation](https://mlsanity.com/paper/2203.11849/) (2022)
- [Crowdsourcing on Sensitive Data with Privacy-Preserving Text Rewriting](https://mlsanity.com/paper/2303.03053/) (2023)
- [Making Translators Privacy-aware on the User's Side](https://mlsanity.com/paper/2312.04068/) (2023)
- [Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guarantees](https://mlsanity.com/paper/2508.20736/) (2025)
- [Zero-Shot Privacy-Aware Text Rewriting via Iterative Tree Search](https://mlsanity.com/paper/2509.20838/) (2025)
- [Reproduction and Replication of an Adversarial Stylometry Experiment](https://mlsanity.com/paper/2208.07395/) (2022)
- [Inspecting the Representation Manifold of Differentially-Private Text](https://mlsanity.com/paper/2503.14991/) (2025)
- [Defending Against Authorship Identification Attacks](https://mlsanity.com/paper/2310.01568/) (2023)
- [Investigating User Perspectives on Differentially Private Text Privatization](https://mlsanity.com/paper/2503.09338/) (2025)
- [Protecting Anonymous Speech: A Generative Adversarial Network Methodology for Removing Stylistic Indicators in Text](https://mlsanity.com/paper/2110.09495/) (2021)

## Abstract (arXiv)

Most of privacy protection studies for textual data focus on removing explicit sensitive identifiers. However, personal writing style, as a strong indicator of the authorship, is often neglected. Recent studies, such as SynTF, have shown promising results on privacy-preserving text mining. However, their anonymization algorithm can only output numeric term vectors which are difficult for the recipients to interpret. We propose a novel text generation model with a two-set exponential mechanism for authorship anonymization. By augmenting the semantic information through a REINFORCE training reward function, the model can generate differentially private text that has a close semantic and similar grammatical structure to the original text while removing personal traits of the writing style. It does not assume any conditioned labels or paralleled text data for training. We evaluate the performance of the proposed model on the real-life peer reviews dataset and the Yelp review dataset. The result suggests that our model outperforms the state-of-the-art on semantic preservation, authorship obfuscation, and stylometric transformation.