TU Darmstadt / ULB / TUbiblio

Natural Language Watermarking for German Texts

Halvani, Oren and Steinebach, Martin and Wolf, Patrick and Zimmermann, Ralf (2013):
Natural Language Watermarking for German Texts.
In: Proceedings of The 1st ACM Workshop on Information Hiding and Multimedia Security (IH & MMSEC 2013), June 17-19, 2013 Montpellier, France, Montpellier, France, In: IH&MMSec '13, ISBN 978-1-4503-2081-8,
DOI: 10.1145/2482513.2482522, [Conference or Workshop Item]

Abstract

In this paper we present four informed natural language watermark embedding methods, which operate on the lexical and syntactic layer of German texts. Our scheme provides several benefits in comparison to state-of-the-art approaches, as for instance that it is not relying on complex NLP operations like full sentence parsing, word sense disambiguation, named entity recognition or semantic role parsing. Even rich lexical resources (e.g. WordNet or the Collins thesaurus), which play an essential role in many previous approches, are unnecessary for our system. Instead, our methods require only a Part-Of-Speech Tagger, simple wordlists that act as black- and whitelists and a trained classifier, which automatically predicts the ability of potential lexical or syntactic patterns to carry portions of the watermark message. Besides this, a part of the proposed methods can be easily adapted into other Indo-European languages, since the grammar rules the methods rely on are not restricted only to the German language. Because the methods perform only lexical and minor syntactic transformations, the watermarked text is not affected by grammatical distortion and simultaneously the meaning of the text is preserved in 82,14% of the cases.

Item Type: Conference or Workshop Item
Erschienen: 2013
Creators: Halvani, Oren and Steinebach, Martin and Wolf, Patrick and Zimmermann, Ralf
Title: Natural Language Watermarking for German Texts
Language: ["languages_typename_1" not defined]
Abstract:

In this paper we present four informed natural language watermark embedding methods, which operate on the lexical and syntactic layer of German texts. Our scheme provides several benefits in comparison to state-of-the-art approaches, as for instance that it is not relying on complex NLP operations like full sentence parsing, word sense disambiguation, named entity recognition or semantic role parsing. Even rich lexical resources (e.g. WordNet or the Collins thesaurus), which play an essential role in many previous approches, are unnecessary for our system. Instead, our methods require only a Part-Of-Speech Tagger, simple wordlists that act as black- and whitelists and a trained classifier, which automatically predicts the ability of potential lexical or syntactic patterns to carry portions of the watermark message. Besides this, a part of the proposed methods can be easily adapted into other Indo-European languages, since the grammar rules the methods rely on are not restricted only to the German language. Because the methods perform only lexical and minor syntactic transformations, the watermarked text is not affected by grammatical distortion and simultaneously the meaning of the text is preserved in 82,14% of the cases.

Title of Book: Proceedings of The 1st ACM Workshop on Information Hiding and Multimedia Security (IH & MMSEC 2013), June 17-19, 2013 Montpellier, France
Series Name: IH&MMSec '13
ISBN: 978-1-4503-2081-8
Uncontrolled Keywords: Secure Data;information hiding, natural language watermarking, performance, syntactic analysis, text watermarking
Divisions: LOEWE > LOEWE-Zentren > CASED – Center for Advanced Security Research Darmstadt
20 Department of Computer Science > Databases and Distributed Systems
LOEWE > LOEWE-Zentren
20 Department of Computer Science
LOEWE
Event Location: Montpellier, France
Date Deposited: 30 Dec 2016 20:23
DOI: 10.1145/2482513.2482522
Identification Number: TUD-CS-2013-0109
Export:

Optionen (nur für Redakteure)

View Item View Item