# TAROT: Task-Oriented Authorship Obfuscation Using Policy Optimization Methods

arXiv: https://arxiv.org/abs/2407.21630 · HTML: https://mlsanity.com/paper/2407.21630/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 43 references that are in the map.
- First posted on arXiv 31 Jul 2024.

## Builds on (most cited first, 15 of 15)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [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)
- [Locally Differentially Private Document Generation Using Zero Shot Prompting](https://mlsanity.com/paper/2310.16111/) (2023)
- [Leveraging Hierarchical Representations for Preserving Privacy and Utility in Text](https://mlsanity.com/paper/1910.08917/) (2019)
- [Keep it Simple: Unsupervised Simplification of Multi-Paragraph Text](https://mlsanity.com/paper/2107.03444/) (2021)
- [Authorship Style Transfer with Policy Optimization](https://mlsanity.com/paper/2403.08043/) (2024)
- [JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models](https://mlsanity.com/paper/2402.08761/) (2024)
- [ALISON: Fast and Effective Stylometric Authorship Obfuscation](https://mlsanity.com/paper/2402.00835/) (2024)

## Built on by (most cited first, 5 of 5)

- [Mitigating Self-Preference by Authorship Obfuscation](https://mlsanity.com/paper/2512.05379/) (2025)
- [A Survey on Current Trends and Recent Advances in Text Anonymization](https://mlsanity.com/paper/2508.21587/) (2025)
- [Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymization](https://mlsanity.com/paper/2506.05979/) (2025)
- [Recipient Profiling: Predicting Characteristics from Messages](https://mlsanity.com/paper/2412.12954/) (2024)
- [Introducing the Privacy-HSD Trade-off: Hate Speech Detection, but not at the Cost of Privacy](https://mlsanity.com/paper/2608.19006/) (2026)

## Abstract (arXiv)

Authorship obfuscation aims to disguise the identity of an author within a text by altering the writing style, vocabulary, syntax, and other linguistic features associated with the text author. This alteration needs to balance privacy and utility. While strong obfuscation techniques can effectively hide the author's identity, they often degrade the quality and usefulness of the text for its intended purpose. Conversely, maintaining high utility tends to provide insufficient privacy, making it easier for an adversary to de-anonymize the author. Thus, achieving an optimal trade-off between these two conflicting objectives is crucial. In this paper, we propose TAROT: Task-Oriented Authorship Obfuscation Using Policy Optimization, a new unsupervised authorship obfuscation method whose goal is to optimize the privacy-utility trade-off by regenerating the entire text considering its downstream utility. Our approach leverages policy optimization as a fine-tuning paradigm over small language models in order to rewrite texts by preserving author identity and downstream task utility. We show that our approach largely reduces the accuracy of attackers while preserving utility. We make our code and models publicly available.