Share Email Print

Proceedings Paper

Natural language watermarking: challenges in building a practical system
Author(s): Mercan Topkara; Giuseppe Riccardi; Dilek Hakkani-Tür; Mikhail J. Atallah
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper gives an overview of the research and implementation challenges we encountered in building an end-to-end natural language processing based watermarking system. With natural language watermarking, we mean embedding the watermark into a text document, using the natural language components as the carrier, in such a way that the modifications are imperceptible to the readers and the embedded information is robust against possible attacks. Of particular interest is using the structure of the sentences in natural language text in order to insert the watermark. We evaluated the quality of the watermarked text using an objective evaluation metric, the BLEU score. BLEU scoring is commonly used in the statistical machine translation community. Our current system prototype achieves 0.45 BLEU score on a scale [0,1].

Paper Details

Date Published: 15 February 2006
PDF: 12 pages
Proc. SPIE 6072, Security, Steganography, and Watermarking of Multimedia Contents VIII, 60720A (15 February 2006); doi: 10.1117/12.643560
Show Author Affiliations
Mercan Topkara, Purdue Univ. (United States)
Giuseppe Riccardi, Univ. of Trento (Italy)
Dilek Hakkani-Tür, AT&T Research Labs. (United States)
Mikhail J. Atallah, Purdue Univ. (United States)

Published in SPIE Proceedings Vol. 6072:
Security, Steganography, and Watermarking of Multimedia Contents VIII
Edward J. Delp III; Ping Wah Wong, Editor(s)

© SPIE. Terms of Use
Back to Top