Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

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

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.

Item is

Basisdaten

einblenden: ausblenden:
Genre: Forschungspapier
Latex : $A^{4}NT$: Author Attribute Anonymity by Adversarial Training of Neural Machine Translation

Dateien

einblenden: Dateien
ausblenden: Dateien
:
arXiv:1711.01921.pdf (Preprint), 745KB
 
Datei-Permalink:
-
Name:
arXiv:1711.01921.pdf
Beschreibung:
File downloaded from arXiv at 2017-11-09 08:02
OA-Status:
Sichtbarkeit:
Privat
MIME-Typ / Prüfsumme:
application/pdf
Technische Metadaten:
Copyright Datum:
-
Copyright Info:
-

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Shetty, Rakshith1, Autor           
Schiele, Bernt1, Autor           
Fritz, Mario1, Autor           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              

Inhalt

einblenden:
ausblenden:
Schlagwörter: Computer Science, Cryptography and Security, cs.CR,Computer Science, Computation and Language, cs.CL,Computer Science, Computers and Society, cs.CY,cs.SI,Statistics, Machine Learning, stat.ML
 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.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 2017-11-062017-11-072017
 Publikationsstatus: Online veröffentlicht
 Seiten: 15 p.
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: arXiv: 1711.01921
URI: http://arxiv.org/abs/1711.01921
BibTex Citekey: shettyANT17arxiv
 Art des Abschluß: -

Veranstaltung

einblenden:

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle

einblenden: