A^4NT: Author Attribute Anonymity by Adversarial Training of Neural Machine Translation

by   Rakshith Shetty, et al.

Text-based analysis methods allow to reveal privacy relevant author attributes such as gender, age and identify of the text's author. Such methods can compromise the privacy of an anonymous author even when the author tries to remove privacy sensitive content. In this paper, we propose an automatic method, called Adversarial Author Attribute Anonymity Neural Translation (A^4NT), to combat such text-based adversaries. We combine sequence-to-sequence language models used in machine translation and generative adversarial networks to obfuscate author attributes. Unlike machine translation techniques which need paired data, our method can be trained on unpaired corpora of text containing different authors. Importantly, we propose and evaluate techniques to impose constraints on our A^4NT to preserve the semantics of the input text. A^4NT learns to make minimal changes to the input text to successfully fool author attribute classifiers, while aiming to maintain the meaning of the input. We show through experiments on two different datasets and three settings that our proposed method is effective in fooling the author attribute classifiers and thereby improving the anonymity of authors.


page 1

page 2

page 3

page 4


Towards Robust and Privacy-preserving Text Representations

Written text often provides sufficient clues to identify the author, the...

The Life of Lazarillo de Tormes and of His Machine Learning Adversities

Summit work of the Spanish Golden Age and forefather of the so-called pi...

DRAG: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting

Author stylized rewriting is the task of rewriting an input text in a pa...

Personalized Machine Translation: Preserving Original Author Traits

The language that we produce reflects our personality, and various perso...

How Different Text-preprocessing Techniques Using The BERT Model Affect The Gender Profiling of Authors

Forensic author profiling plays an important role in indicating possible...

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

With Internet users constantly leaving a trail of text, whether through ...

Probing Classifiers are Unreliable for Concept Removal and Detection

Neural network models trained on text data have been found to encode und...

Please sign up or login with your details

Forgot password? Click here to reset