Campus Event Calendar
Event Entry
What and Who
Feature Mining and Intelligent Computing of Audio Steganalysis
Mengyu Qiao
Beijing University of Posts and Telecommunications, China
PhD Application Talk
AG 1, AG 3, AG 4, AG 5, SWS, RG1, MMCI
Public Audience
English
Note: We use this to send email in the morning.
Date, Time and Location
Tuesday, 14 July 2009
09:00
240 Minutes
E1 4
024
Saarbrücken
Abstract
Steganography is a serious concern of information assurance due to the unknown extent to which it may be used by criminals, terrorists, etc. Several steganographic systems are developed to employ digital audio as carrier for covert communication. To detect the information-hiding, we extract neighboring joint probability and Markov transition features on the second derivative. A support vector machine is applied to the features for discovery of the existence of covert message in digital audios. Signal complexity and information-hiding ratio are introduced to evaluate the performance of proposed methods. Experimental results show that our approach is successful to discriminate covers and steganograms, even with low embedding ratio and high signal complexity.
Contact
IMPRS Office Team
0681 9325 225
--email hidden
passcode not visible
logged in users only
Stephanie Jörg, 07/08/2009 12:10 -- Created document.