Dissemin is shutting down on January 1st, 2025

Published in

Security, Steganography, and Watermarking of Multimedia Contents VII

DOI: 10.1117/12.586941

Links

Tools

Export citation

Search in Google Scholar

Steganalysis of recorded speech

Proceedings article published in 2005 by Micah Kimo Johnson, Siwei Lyu ORCID, Hany Farid
This paper is available in a repository.
This paper is available in a repository.

Full text: Download

Red circle
Preprint: archiving forbidden
Green circle
Postprint: archiving allowed
Green circle
Published version: archiving allowed
Data provided by SHERPA/RoMEO

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 underlyingstatistics of audiosignals. Our statistical model begins by buildinga 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.