English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Text-based analysis methods allow to reveal privacy relevant authorattributes such as gender, age and identify of the text's author. Such methodscan compromise the privacy of an anonymous author even when the author tries toremove privacy sensitive content. In this paper, we propose an automaticmethod, called Adversarial Author Attribute Anonymity Neural Translation($A^4NT$), to combat such text-based adversaries. We combinesequence-to-sequence language models used in machine translation and generativeadversarial networks to obfuscate author attributes. Unlike machine translationtechniques which need paired data, our method can be trained on unpairedcorpora of text containing different authors. Importantly, we propose andevaluate techniques to impose constraints on our $A^4NT$ to preserve thesemantics of the input text. $A^4NT$ learns to make minimal changes to theinput text to successfully fool author attribute classifiers, while aiming tomaintain the meaning of the input. We show through experiments on two differentdatasets and three settings that our proposed method is effective in foolingthe author attribute classifiers and thereby improving the anonymity ofauthors.

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