ISE: AN INTELLIGENT AND EFFICIENT STEGANALYSIS ENGINE FOR IMAGE DATABASE IN BIG DATA SYSTEMS

Details

Hits: 3439

Volume 1 (1), July 2018, Pages 42-50

Mayank Tiwary¹, Pritish Mishra¹, Mohammad S. Obaidat², Deepak Puthal³

¹ SAP Lab, Bangalore, India, This email address is being protected from spambots. You need JavaScript enabled to view it., This email address is being protected from spambots. You need JavaScript enabled to view it.

² Department of ECE, Nazarbayev University, Astana, Kazakhstan;] King Abdullah II School of Information Technology, The University of Jordan, Jordan, Ministry of Education Overseas Distinguished Professor at University of Science and Technology Beijing, China, This email address is being protected from spambots. You need JavaScript enabled to view it.

³ University of Technology Sydney, Australia, This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

The aim of this work is to design a faster and artificially intelligent steganalysis engine, which is able to secure the image databases from any infected image in big data environment. The proposed Intelligent Steganalysis Engine (ISE) for image database in big data makes use of three steps, which are image estimation, feature generation and classification. In the first step, five new images are estimated from the original image, for computing 438 features and then these data images are passed through a classifier for final prediction of a stego image. The engine is designed based on Map-Reduce programming approach to cope with big data. The actual experiments were performed on the Big Data Hadoop by taking standard image data set. In the first two steps, the images are processed in both spatial and DCT domain. During these steps the implementations of image estimation and feature extraction algorithms become very much computationally intensive and seek a huge amount of time. The results obtained are compared with previously reported six similar works and an inference has been drawn for appropriate use of feature set and classifier pair.

Keywords:

Big Data, HPC, Steganalysis, Map, GPU, Hadoop, CUDA

DOI: https://doi.org/10.32010/26166127.2018.1.1.42.50

References

[1] Lyu, S., Farid, H. (2002) Detecting Hidden Messages Using HigherOrder Statistics and Support Vector Machines, Proceedings of the 5th International Workshop on Information Hiding (pp.340-354). Noordwijkerhout: Springer.

[2] Harmsen, J.J., Pearlman, W. A. (2003) Steganalysis of Additive Noise Modelable Information Hiding, Proceedings of SPIE - The International Society for Optical Engineering, 5020, 131-142.

[3] Fridrich, J. (2004) Feature-based Steganalysis for JPEG Images and Its Implications for Future Design of Steganographic Schemes, Proceedings of the 6th International Information Hiding Workshop (pp.67-81). Toronto: Springer

[4] Shi, Y. Q., Chen, C. H., Chen, W. (2007) A Markov process based approach to effective attacking JPEG steganography, Proceedings of the 8th Information Hiding Workshop (pp.249-264). Alexandria: Springer

[5] Li, Z., Lu, K.J., Zeng, X.T., Pan, X.Z. (2009) Feature-Based Steganalysis for JPEG Images, Proceedings of the 1st International Conference on Digital Image Processing (pp.76-80).

[6] Zhang, Q., Liu, Y., Zhang, Sh., Chen, K. (2009) Classification Method of Jsteg Stego-Images and F5 Stego-Image, Proceedings of the Fourth International Conference on Innovative Computing, Information and Control (ICICIC) (pp.394-397). Kaohsiung, Taiwan.

[7] Westfeld, A. (2002) Detecting low embedding rates, Proceedings of the 5th International Workshop on Information Hiding (pp.324-339). Noordwijkerhout: Springer.

[8] Chen, M., Agaian, S.S., Chen, C.L.P., Rodriguez, B.M. (2009) Alpha-trimmed image estimation for JPEG steganography detection, Proceedings of IEEE International Conference on Systems, Man and Cybernetics (pp.4581-4585). San Antonio, USA.

[9] Yu, W, Li, Z., Ping, L. (2010) Blind detection for JPEG steganography, Proceedingsof the International Conference on Networking and Information Technology (pp.128- 132). Manila, Philippines.

[10] Bansal, D., Chhikara, R. (2014) Performance Evaluation of Steganography Tools Using SVM and NPR Tool, Proceedings of the 4th International Conference on Advanced Computing and Communication Technologies (ACCT) (pp.483-487). Rohtak, India.

[11] Oplatkova, Z., Holoska, J., Zelinka, I., Senkerik, R. (2009) Detection of Steganography Inserted by OutGuess and Steghide by Means of Neural Networks, Proceedings of the 3rd Asia International Conference on Modelling and Simulation (pp.7-12).

[12] Ker, A.D. (2005) Steganalysis of LSB matching in grayscale images, IEEE Signal Processing Letters, 12(6), 441-444.

[13] Zhi-Min, H.; Ng, W.W.Y., Chan, P.P.K., Yeung, D.S. (2010) Steganography detection using localized generalization error model, Proceedings of the IEEE International Conference on Systems Man and Cybernetics (pp.1544-1549).

[14] Xu, M., Li, T., Ping, X. (2009) Estimation of MB steganography based on least square method, Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, (pp.1509-1512).

[15] Li, X., Zeng, T., Yang, B. (2008) A further study on steganalysis of LSB matching by calibration, Proceedings of the 15th IEEE International Conference on Image Processing, (pp.2072 – 2075).

[16] Nvidia MPS. (2015, February 19). Retrieved from: https://docs.nvidia.com/ deploy/pdf/CUDA Multi Process Service Overview.pdf

[17] Bas, P., Furon, T. (2015, February 19). Break our watermarking system, second edition. Retrieved from: http://bows2.gipsa-lab.inpg.fr/. [18] Chang, C. C., Lin C. L. (2011) LIBSVM: A Library for Support Vector, ACM Transactions on Intelligent Systems and Technology, 2 (3), 1-27.

[19] Tiwary, M., Priyadarshini R., Misra, R. (2014) A faster and intelligent steganography detection using Graphics Processing Unit in cloud. Proceedings of the International Conference on High Performance Computing and Applications (pp.1-6). Bhubaneswar, India.