Scholarly record

DETECTOR OF THE STEGANOGRAPHY IMAGES WITH THE APPLICATION OF ARTIFICIAL NEURAL NETWORK

Ing. Jakub Hendrych, Prof. Lacezar Licev, Ing. Radim Kuncicky

Abstract

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 пїЅblind steganalysisпїЅ, 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.

Publication Impact Profile

• Citations
• CrossRef - Citation Indexes: 1
• Scopus - Citation Indexes: 1

• Captures
• Mendeley - Readers: 1

PLUMX see details

DOI resolver: doi.org/10.5593/sgem2017/21/s07.033

Publication details

Back to publication list