Share Email Print
cover

Proceedings Paper

Steganalysis of recorded speech
Author(s): Micah K. Johnson; Siwei Lyu; Hany Farid
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Digital audio provides a suitable cover for high-throughput steganography. At 16 bits per sample and sampled at a rate of 44,100 Hz, digital audio has the bit-rate to support large messages. In addition, audio is often transient and unpredictable, facilitating the hiding of messages. Using an approach similar to our universal image steganalysis, we show that hidden messages alter the underlying statistics of audio signals. Our statistical model begins by building a linear basis that captures certain statistical properties of audio signals. A low-dimensional statistical feature vector is extracted from this basis representation and used by a non-linear support vector machine for classification. We show the efficacy of this approach on LSB embedding and Hide4PGP. While no explicit assumptions about the content of the audio are made, our technique has been developed and tested on high-quality recorded speech.

Paper Details

Date Published: 21 March 2005
PDF: 9 pages
Proc. SPIE 5681, Security, Steganography, and Watermarking of Multimedia Contents VII, (21 March 2005); doi: 10.1117/12.586941
Show Author Affiliations
Micah K. Johnson, Dartmouth College (United States)
Siwei Lyu, Dartmouth College (United States)
Hany Farid, Dartmouth College (United States)


Published in SPIE Proceedings Vol. 5681:
Security, Steganography, and Watermarking of Multimedia Contents VII
Edward J. Delp; Ping W. Wong, Editor(s)

© SPIE. Terms of Use
Back to Top