Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Hybrid SOFM–MLP Neural Network for Steganalysis to Detect Stego-Contents in Corporate Emails


Affiliations
1 Department of Informatics, Wollega University, Nekemte, Ethiopia
     

   Subscribe/Renew Journal


A hybrid approach of cryptography, data compression and steganography has been proposed in this paper. Motivation behind this research is to provide a smart image steganographic technique which must be capable enough to provide better quality stego-image with a high data hiding capability. Proposed approach is a LSB based approach in the field of image steganography. Maximum data hiding capability of proposed approach will be evaluated from kekre's algorithm. Proposed approach hides data in the upper LSB bit only when its adjacent LSB bit of all the pixel have conceived a bit of secret data for better quality of the stego-image. LZW compression scheme is used to optimize the size of secret data, it will enable a personal to hide approx 2 times more data in a cover-image. This approach is secure against the detection attack and its stego-image is totally indistinguishable from the original image (cover-image) by the human eye.

Keywords

Steganography, Pixel-Value Differencing, Pixel Component, Stego-Image.
User
Subscription Login to verify subscription
Notifications
Font Size

  • Ali Akcayol, M & Can Cinar 2005, ‘Artificial neural network based modeling of heated catalytic converter performance’, Applied Thermal Engineering, vol. 25, pp. 2341-2350.
  • Amir AbolfazlSuratgar, Abbas Hoseinabadi & Mohammad Bagher Tavakoli 2007, ‘Modified Levenberg-Marquardt method for neural Networks training’, Journal of Computer, Inforrmation, System and Control Engineering, vol. 1, pp 1748-1750.
  • Bell, G & Yeuan-Kuen Lee, 2010, ‘A Method for Automatic Identification of Signatures of Steganography Software’, IEEE Transactions on Information Forensics and Security, vol. 5, no. 2, pp. 354-358.
  • Bender, W, Gruhl, D, Morimoto, N & Lu, A 1996, ‘Techniques for data hiding’, IBM Syst. J., vol. 35, no.3, pp. 313-336.
  • Chun-Hsiang Huang, Shang-Chih Chuang & Ja-Ling Wu 2008, ‘Digital-Invisible-Ink Data Hiding Based on Spread-Spectrum and Quantization Techniques’, IEEE Transactions on Multimedia, vol. 10, no. 4, pp. 557-569.
  • Clair & Bryan 2005, Steganography: How to Send a Secret Message. Available from: .
  • Neil Johnson, F 2005, History and Steganography. Available from :< http://www.jjtc.com/stegdoc/sec202.html>.
  • Min-Wen Chao, Chao-hung Lin, Cheng-Wei Yu & Tong-Yee Lee, 2009, ‘A High Capacity 3D Steganography Algorithm’, IEEE Transactions on Visualization and Computer Graphics, vol. 15, no. 2, pp. 274-284.

Abstract Views: 357

PDF Views: 2




  • Hybrid SOFM–MLP Neural Network for Steganalysis to Detect Stego-Contents in Corporate Emails

Abstract Views: 357  |  PDF Views: 2

Authors

P. T. Anitha
Department of Informatics, Wollega University, Nekemte, Ethiopia

Abstract


A hybrid approach of cryptography, data compression and steganography has been proposed in this paper. Motivation behind this research is to provide a smart image steganographic technique which must be capable enough to provide better quality stego-image with a high data hiding capability. Proposed approach is a LSB based approach in the field of image steganography. Maximum data hiding capability of proposed approach will be evaluated from kekre's algorithm. Proposed approach hides data in the upper LSB bit only when its adjacent LSB bit of all the pixel have conceived a bit of secret data for better quality of the stego-image. LZW compression scheme is used to optimize the size of secret data, it will enable a personal to hide approx 2 times more data in a cover-image. This approach is secure against the detection attack and its stego-image is totally indistinguishable from the original image (cover-image) by the human eye.

Keywords


Steganography, Pixel-Value Differencing, Pixel Component, Stego-Image.

References





DOI: https://doi.org/10.36039/ciitaas%2F10%2F1%2F2018%2F167836.5-9