An artificial neural network for wavelet steganalysis

Abstract

Hiding messages in image data, called steganography, is used for both legal and illicit purposes. The detection of hidden messages in image data stored on websites and computers, called steganalysis, is of prime importance to cyber forensics personnel. Automating the detection of hidden messages is a requirement, since the shear amount of image data stored on computers or websites makes it impossible for a person to investigate each image separately. This paper describes research on a prototype software system that automatically classifies an image as having hidden information or not, using a sophisticated artificial neural network (ANN) system. An ANN software package, the ISU ACL NetWorks Toolkit, is trained on a selection of image features that distinguish between stego and nonstego images. The novelty of this ANN is that it is a blind classifier that gives more accurate results than previous systems. It can detect messages hidden using a variety of different types of embedding algorithms. A Graphical User Interface (GUI) combines the ANN, feature selection, and embedding algorithms into a prototype software package that is not currently available to the cyber forensics community. ABSTRACTHiding messages in image data, called steganography, is used for both legal and illicit purposes. The detection of hidden messages in image data stored on websites and computers, called steganalysis, is of prime importance to cyber forensics personnel. Automating the detection of hidden messages is a requirement, since the shear amount of image data stored on computers or websites makes it impossible for a person to investigate each image separately. This paper describes research on a prototype software system that automatically classifies an image as having hidden information or not, using a sophisticated artificial neural network (ANN) system. An ANN software package, the ISU ACL NetWorks Toolkit, is trained on a selection of image features that distinguish between stego and nonstego images. The novelty of this ANN is that it is a blind classifier that gives more accurate results than previous systems. It can detect messages hidden using a variety of different types of embedding algorithms. A Graphical User Interface (GUI) combines the ANN, feature selection, and embedding algorithms into a prototype software package that is not currently available to the cyber forensics community.

Recent Advances in Steganography

“…This method depends on dynamic steganalysis problems that consist of estimate length of concealed message, detect security key stego files, estimate amount of MPVD and etc. (Davidson et al, 2005) There are total of 1300 images, which had been cleared of copyright issues. (http://www.datahiding.org), courtesy of Dr. Edward Delp, Purdue University (Tan et al, 2006) Three hundred images are randomly selected from human, architecture and landscape categories of photo.net image database, one hundred images from each category.…”

Steganalysis Using KL Transform and Radial Basis Neural Network

“…Automating the detection of hidden messages is a requirement, since the shear amount of image data stored on computers or websites makes it impossible for a person to investigate each image separately [5].…”

“…Artificial Neural Networks (ANNs) have been shown over the past two decades to provide solutions to data mining-type problems that are not easily manipulated by classical solutions [5].…”

Image Steganalysis in Frequency Domain Using Co-Occurrence Matrix and Bpnn

“…Steganalysis tools are essential for Internet security professionals. Law enforcement agencies need good programs that can identify suspicious files on the computer or the Web [5].…”