$A^{4}NT$: Author Attribute Anonymity by Adversarial Training of Neural Machine Translation
This addresses privacy concerns for anonymous authors in text analysis, though it is incremental as it builds on existing adversarial and translation techniques.
The paper tackles the problem of preserving author privacy against text-based attribute classifiers by proposing A^4NT, a method that uses adversarial training of neural machine translation to obfuscate attributes like gender and age while maintaining text semantics, showing effectiveness in fooling classifiers across datasets.
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.