de.mpg.escidoc.pubman.appbase.FacesBean
Deutsch
 
Hilfe Wegweiser Impressum Kontakt Einloggen
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT

Freigegeben

Forschungspapier

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

MPG-Autoren
http://pubman.mpdl.mpg.de/cone/persons/resource/persons206357

Shetty,  Rakshith
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons45383

Schiele,  Bernt
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons44451

Fritz,  Mario
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

Externe Ressourcen
Es sind keine Externen Ressourcen verfügbar
Volltexte (frei zugänglich)

arXiv:1711.01921.pdf
(Preprint), 745KB

Ergänzendes Material (frei zugänglich)
Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar
Zitation

Shetty, R., Schiele, B., & Fritz, M. (2017). A^4NT: Author Attribute Anonymity by Adversarial Training of Neural Machine Translation. Retrieved from http://arxiv.org/abs/1711.01921.


Zitierlink: http://hdl.handle.net/11858/00-001M-0000-002E-271D-B
Zusammenfassung
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.