A NEW STEGANALYSIS FRAMEWORK TO DETECT STEGO-CONTENTS IN CORPORATE EMAILS USING BACK PROPAGATION NEURAL NETWORK WITH MODIFIED LEVENBERG-MARQUARDT ALGORITHM FOR LEARNING

Anitha Shyam

Abstract


ABSTRACT

Steganography is used to hide the occurrence of communication. The goal of steganalysis is to detect and/or estimate potentially hidden information from observed data with little or no knowledge about the steganography algorithm and/or its parameters. Steganalysis is the science of detecting the presence of hidden data in the cover media files.

The long term goal is to develop a steganalysis framework that can work effectively at least for a class of steganography methods if not for all. Neural network methods are used to analyze the statistical knowledge of the image. Training the patterns of the image strengthen the detection efficiency of the algorithm. The analysis of these algorithms and performance impact of a network are taken as the research work.  In order to further improve the prediction accuracy this proposed approach uses Modified Levenberg-Marquardt (LM) algorithm for neural network learning with modified parameters. The primary aim of this research is to propose the novel technique for the steganalysis using neural networks to overcome the above given problems and to effectively detect the stego-contents in corporate emails.

Keywords: Steganography, Steganalysis, Artificial Neural Network, Neural Network.


Full Text:

PDF

References


Amir Abolfazl Suratgar, Mohammad Bagher Tavakoli and Abbas Hoseinabadi “Modified Levenberg-Marquardt Method for Neural Networks Training”, World Academy of Science, Engineering and Technology, pp. 46-48, 2005.

Bin Li, Yanmei Fang and Jiwu Huang “Steganalysis of Multiple-Base Notational System Steganography”, IEEE Signal Processing Letters, Vol.15, pp. 493-496, 2008.

Chi Z, Wu J, and Yan H “Handwritten numeral character recognition using self-organizing maps and fuzzy rules,” Pattern Recognit., Vol. 28, No.1, pp. 59–66, 1995.

Donovan Artz, “Digital Steganography: Hiding Data within Data”, IEEE Internet Computing, pp. 75-80, 2001.

Farras O and Padro C “Ideal Hierarchical Secret Sharing Schemes”, IEEE Transactions on Information Theory, Vol. 8, No. 5, pp. 3273-3286, 2012.

Pal N R and Chintalapudi K, “A connectionist system for feature selection,” Neural, Parallel Sci. Computat., Vol. 5, No. 3, pp. 359–381, 1997.

Ping Chang and Jeng-Shong Shih, “The Application of Back Propagation Neural Network of Multi-channel Piezoelectric Quartz Crystal Sensor for Mixed Organic Vapours”, Tamkang Journal of Science and Engineering, Vol. 5, No. 4, pp. 209-217, 2002.

Nasarabadi N M and Feng Y, “Vector quantization of images based on kohonen self-organizing feature maps,” Proc. IEEE International. Conference on Neural Networks, pp. I-101–I-108, 1988.




DOI: http://dx.doi.org/10.1000/ijses.v0i0.93

Refbacks

  • There are currently no refbacks.


Copyright (c) 2016 International Journal Series in Engineering Science (IJSES) (ISSN: 2455-3328)

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.