# Protecting Anonymous Speech: A Generative Adversarial Network Methodology for Removing Stylistic Indicators in Text

arXiv: https://arxiv.org/abs/2110.09495 · HTML: https://mlsanity.com/paper/2110.09495/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 62 references that are in the map.
- First posted on arXiv 18 Oct 2021.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient](https://mlsanity.com/paper/1609.05473/) (2016)
- [GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium](https://mlsanity.com/paper/1706.08500/) (2017)
- [Advances in Pre-Training Distributed Word Representations](https://mlsanity.com/paper/1712.09405/) (2017)
- [Bridging the Gap between Training and Inference for Neural Machine Translation](https://mlsanity.com/paper/1906.02448/) (2019)
- [Long Text Generation via Adversarial Training with Leaked Information](https://mlsanity.com/paper/1709.08624/) (2017)
- [MaskGAN: Better Text Generation via Filling in the______](https://mlsanity.com/paper/1801.07736/) (2018)
- [BLEU is Not Suitable for the Evaluation of Text Simplification](https://mlsanity.com/paper/1810.05995/) (2018)
- [Unsupervised Text Style Transfer using Language Models as Discriminators](https://mlsanity.com/paper/1805.11749/) (2018)
- [Separating Style and Content for Generalized Style Transfer](https://mlsanity.com/paper/1711.06454/) (2017)
- [A Twofold Siamese Network for Real-Time Object Tracking](https://mlsanity.com/paper/1802.08817/) (2018)
- [A4NT: Author Attribute Anonymity by Adversarial Training of Neural Machine Translation](https://mlsanity.com/paper/1711.01921/) (2017)
- [ER-AE: Differentially Private Text Generation for Authorship Anonymization](https://mlsanity.com/paper/1907.08736/) (2019)
- [Character-level and Multi-channel Convolutional Neural Networks for Large-scale Authorship Attribution](https://mlsanity.com/paper/1609.06686/) (2016)
- [Siamese Networks for Large-Scale Author Identification](https://mlsanity.com/paper/1912.10616/) (2019)
- [When Coding Style Survives Compilation: De-anonymizing Programmers from Executable Binaries](https://mlsanity.com/paper/1512.08546/) (2015)
- [Style Obfuscation by Invariance](https://mlsanity.com/paper/1805.07143/) (2018)

## Abstract (arXiv)

With Internet users constantly leaving a trail of text, whether through blogs, emails, or social media posts, the ability to write and protest anonymously is being eroded because artificial intelligence, when given a sample of previous work, can match text with its author out of hundreds of possible candidates. Existing approaches to authorship anonymization, also known as authorship obfuscation, often focus on protecting binary demographic attributes rather than identity as a whole. Even those that do focus on obfuscating identity require manual feedback, lose the coherence of the original sentence, or only perform well given a limited subset of authors. In this paper, we develop a new approach to authorship anonymization by constructing a generative adversarial network that protects identity and optimizes for three different losses corresponding to anonymity, fluency, and content preservation. Our fully automatic method achieves comparable results to other methods in terms of content preservation and fluency, but greatly outperforms baselines in regards to anonymization. Moreover, our approach is able to generalize well to an open-set context and anonymize sentences from authors it has not encountered before.