# JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models

arXiv: https://arxiv.org/abs/2402.08761 · HTML: https://mlsanity.com/paper/2402.08761/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 48 references that are in the map.
- First posted on arXiv 13 Feb 2024.

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Beyond English-Centric Multilingual Machine Translation](https://mlsanity.com/paper/2010.11125/) (2020)
- [Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models](https://mlsanity.com/paper/1610.02424/) (2016)
- [WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation](https://mlsanity.com/paper/2201.05955/) (2022)
- [Reformulating Unsupervised Style Transfer as Paraphrase Generation](https://mlsanity.com/paper/2010.05700/) (2020)
- [Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation](https://mlsanity.com/paper/1804.06609/) (2018)
- [NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints](https://mlsanity.com/paper/2010.12884/) (2020)
- [A4NT: Author Attribute Anonymity by Adversarial Training of Neural Machine Translation](https://mlsanity.com/paper/1711.01921/) (2017)
- [Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing](https://mlsanity.com/paper/2305.16635/) (2023)
- [Text Style Transfer for Bias Mitigation using Masked Language Modeling](https://mlsanity.com/paper/2201.08643/) (2022)
- [Are You Robert or RoBERTa? Deceiving Online Authorship Attribution Models Using Neural Text Generators](https://mlsanity.com/paper/2203.09813/) (2022)
- [Avengers Ensemble! Improving Transferability of Authorship Obfuscation](https://mlsanity.com/paper/2109.07028/) (2021)
- [A Girl Has A Name: Detecting Authorship Obfuscation](https://mlsanity.com/paper/2005.00702/) (2020)

## Built on by (most cited first, 7 of 7)

- [StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements](https://mlsanity.com/paper/2408.15666/) (2024)
- [Masks and Mimicry: Strategic Obfuscation and Impersonation Attacks on Authorship Verification](https://mlsanity.com/paper/2503.19099/) (2025)
- [TAROT: Task-Oriented Authorship Obfuscation Using Policy Optimization Methods](https://mlsanity.com/paper/2407.21630/) (2024)
- [A Survey on Current Trends and Recent Advances in Text Anonymization](https://mlsanity.com/paper/2508.21587/) (2025)
- [Content Anonymization for Privacy in Long-form Audio](https://mlsanity.com/paper/2510.12780/) (2025)
- [A Survey of Text Style Transfer: Applications and Ethical Implications](https://mlsanity.com/paper/2407.16737/) (2024)
- [I Am No One: Style-Aware Paraphrasing for Text Anonymization](https://mlsanity.com/paper/2609.12341/) (2026)

## Abstract (arXiv)

The permanence of online content combined with the enhanced authorship identification techniques calls for stronger computational methods to protect the identity and privacy of online authorship when needed, e.g., blind reviews for scientific papers, anonymous online reviews, or anonymous interactions in the mental health forums. In this paper, we propose an unsupervised inference-time approach to authorship obfuscation to address the unique challenges of authorship obfuscation: lack of supervision data for diverse authorship and domains, and the need for a sufficient level of revision beyond simple paraphrasing to obfuscate the authorship, all the while preserving the original content and fluency. We introduce JAMDEC, a user-controlled, inference-time algorithm for authorship obfuscation that can be in principle applied to any text and authorship. Our approach builds on small language models such as GPT2-XL in order to help avoid disclosing the original content to proprietary LLM's APIs, while also reducing the performance gap between small and large language models via algorithmic enhancement. The key idea behind our approach is to boost the creative power of smaller language models through constrained decoding, while also allowing for user-specified controls and flexibility. Experimental results demonstrate that our approach based on GPT2-XL outperforms previous state-of-the-art methods based on comparably small models, while performing competitively against GPT3.5 175B, a propriety model that is two orders of magnitudes larger.