DOI: 10.5593/sgem2017/21/S07.033


J. Hendrych, L. Licev, R. Kuncicky
Wednesday 13 September 2017 by Libadmin2017

References: 17th International Multidisciplinary Scientific GeoConference SGEM 2017, www.sgem.org, SGEM2017 Conference Proceedings, ISBN 978-619-7408-01-0 / ISSN 1314-2704, 29 June - 5 July, 2017, Vol. 17, Issue 21, 255-262 pp, DOI: 10.5593/sgem2017/21/S07.033


Steganography can be used for illegal activities. It is very important to be prepared. To detect steganography images we have counter-technique known as steganalysis. There are different types of steganalysis, depending on if the original artifact (cover) is known or not. In terms of practical use, most important are methods of “blind steganalysis”, that can be applied to image files and because we do not have the original cover for comparison. This article deals with the application of neural networks on the issues of steganalysis. The aim is to improve the detection capability of conventional steganalytical tools with using of artificial neural network and several improvements. In our work is important to understand the behavior of the targeted steganography algorithm. Then we can use it is weaknesses to increase the detection capability. In our case we are focus on steganography algorithm OutGuess2.0. We analyze the ability of the detector, which utilizes calibration process and blockiness calculation to detect the presence of steganography message in suspected image. We verify if the deployment of neural network improves this detection.

Keywords: steganography, steganalysis, neural network, ANN, JPEG

Home | Contact | Site Map | Site statistics | Visitors : 0 / 353063

Follow site activity en  Follow site activity INFORMATICS  Follow site activity Papers SGEM2017   ?

CrossRef Member    Indexed in ISI Web Of Knowledge   Indexed in ISI Web Of Knowledge

© Copyright 2001 International Multidisciplinary Scientific GeoConference & EXPO SGEM. All Rights Reserved.

Creative Commons License