Skip to main content
SpringerLink
Log in

A Cognitive Ensemble of Extreme Learning Machines for Steganalysis Based on Risk-Sensitive Hinge Loss Function

  • Published:
Cognitive Computation Aims and scope Submit manuscript

Abstract

In this paper, we propose a risk-sensitive hinge loss function-based cognitive ensemble of extreme learning machine (ELM) classifiers for JPEG steganalysis. ELM is a single hidden-layer feed-forward network that chooses the input parameters randomly and estimates the output weights analytically. For steganalysis, we have extracted 548-dimensional merge features and trained ELM to approximate the functional relationship between the merge features and class label. Further, we use a cognitive ensemble of ELM classifier with risk-sensitive hinge loss function for accurate steganalysis. As the hinge loss error function is shown to be better than mean-squared error function for classification problems, here, the individual ELM classifiers are developed based on hinge loss error function. The cognition in the ensemble of ELM obtains the weighted sum of individual classifiers by enhancing the outputs of winning classifiers for a sample, while penalizing the other classifiers for the sample. Thus, the cognitive ensemble ELM classifier positively exploits the effect of initialization in each classifier to obtain the best results. The performance of the cognitive ensemble ELM in performing the steganalysis is compared to that of a single ELM, and the existing ensemble support vector machine classifier for steganalysis. Performance results show the superior classification ability of the cognitive ensemble ELM classifier.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

References

  1. Avcibus I, Kharrazi M, Memon ND, Sankur B. Image steganalysis with binary similarity measures. In: Proceedings of the 2002 international conference on image processing (ICIP 2002), vol 3, 2002. p. 645–648.

    Article  Google Scholar 

  2. Cambria E, Hussain A. Sentic album: content-, concept-, and context-based online personal photo management system. Cogn Comput. 2012;4(4):477–96.

    Article  Google Scholar 

  3. Cambria E, Hussain A. Sentic computing: techniques, tools, and applications, SpringerBriefs in cognitive computation. Dordrecht: Springer; 2012.

    Book  Google Scholar 

  4. Chen C, Shi YQ. JPEG image steganalysis utilizing both intrablock and interblock correlations. In: Proceedings of the IEEE international symposium on circuits and systems; 2008. p. 3029–3032.

  5. Chen B, Feng GR, Zhang XP, Li FY. Mixing high-dimensional features for JPEG steganalysis with ensemble classifier. Signal Image Video Process. doi:10.1007/s11760-012-0380-7

  6. Cheng C, Tay WP, Huang GB. Extreme learning machines for intrusion detection. The 2012 International Joint Conference on Neural Networks (IJCNN) 2012;1(1):1–8.

    Google Scholar 

  7. Decherchi S, Gastaldo P, Zunino R, Cambria E, Redi J. Circular-elm for the reduced-reference assessment of perceived image quality. Neurocomputing. 2013;102:7889.

    Article  Google Scholar 

  8. Farid H, Siwei L. Detecting hidden messages using higher-order statistics and support vector machines. In: Proceedings of the 5th International Workshop Information Hiding, Lecture Notes in Computer Science, vol 2578. New York: Springer; 2002. p. 340–354.

  9. Feng GR, Huang GB, Lin QP, Gay R. Error minimized extreme learning machine with growth of hidden nodes and incremental learning. IEEE Trans Neural Netw. 2009;20(8):1352–7.

    Article  PubMed  Google Scholar 

  10. Fridrich J. Feature-based steganalysis for jpeg images and its implications for future design of steganographic schemes. Lect Notes Comput Sci. 2004;3200:67–81.

    Article  Google Scholar 

  11. Goljan M, Fridrich J, Holotyak T. New blind steganalysis and its implications. In: Proceedings of the SPIE, Electronic Imaging, Security, Steganography, and Watermarking of Multimedia Contents VIII, vol 6072, 2006. p. 1–13.

  12. Grassi M, Cambria E, Hussain A, Piazza F. Sentic web: a new paradigm for managing social media affective information. In: Cognitive Computation, vol 3, no. 3; 2011. p. 480–489.

  13. Huang G-B. Learning capability and storage capacity of two-hidden layer feedforward networks. IEEE Trans Neural Netw. 2003;14(2):274–81.

    Article  PubMed  Google Scholar 

  14. Huang G-B, Zhu QY, Siew CK. Extreme learning machine: a new learning scheme of feedforward neural network. In: Proceedings of International Joint Conference on Neural Networks (IJCNN2004), vol 2, 2004. p. 985–990.

  15. Huang G-B, Zhu QY, Siew CK. Extreme learning machine: theory and applications. Neurocomputing. 2006;70(1–3):985–90.

    Google Scholar 

  16. Huang G-B, Zhu QY, Siew CK. Real-time learning capability of neural networks. IEEE Trans Neural Netw. 2006;17(4):863–78.

    Article  PubMed  Google Scholar 

  17. Huang G-B, Wang DH, Lan Y. Universal approximation using incremental constructive feedforward network with random hidden nodes. IEEE Trans Neural Netw. 2011;17(4):879–92.

    Article  Google Scholar 

  18. Huang G-B, Zhu QY, Siew CK. Extreme learning machines: a survey. Int J Mach Learn Cybern. 2011;2(2):107–22.

    Article  Google Scholar 

  19. Huang G-B, Zhou H, Ding X, Zhang R. Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern Part B: Cybern. 2012;42(2):513–29.

    Article  Google Scholar 

  20. Huang G.-B. , An Insight into Extreme Learning Machines: Random Neurons, Random Features and Kernels. Cogn Comput. (in press) 2014. doi:10.1007/s12559-014-9255-2.

  21. Kazakov D. The self-cognisant robot. Cogn Comput. 2013;4(3):347–53.

    Article  Google Scholar 

  22. Kodovsky J., Fridrich J., Dittman J. , Craver S., Fridrich J., Calibration revisited. In: Proceedings of the 11th ACM Multimedia & Security Workshop, Princeton, NJ; 2009. p. 63–74.

  23. Kodovsky J, Penvy T, Fririch J, Memon ND, Delp EJ, Wong PW, Dittmann J. Modern steganalysis can detect YASS. In: Proceedings of the SPIE, electronic imaging, security and forensics of multimedia XII, San Jose, CA, vol 7541; 2010. p. 02-01–02-11.

  24. Kodovsky J, Fridrich J, Holub V. Ensemble classifiers for steganalysis of digital media. IEEE Trans Inf Secur Forensics. 2012;7(2):432–44.

    Article  Google Scholar 

  25. Pereira F, Gordon G. The support vector decomposition machine. In: Proceedings of the 23rd international conference on machine learning (ICML 2006), Pittsburgh, PA; 2006. p. 689–696.

  26. Pevny T, Fridrich J. Merging Markov and DCT features for multi-class JPEG steganalysis. In: Proceedings of SPIE, vol 6505, San Jose, CA; 2007. p. 311–314.

  27. Rong HJ, Huang GB, Sundararaajan N, Saratchandran P. Online sequential fuzzy extreme learning machine for function approximation and classification problems. IEEE Trans Syst Man Cybern Part B: Cybern. 2009;39(4):1067–77.

    Article  Google Scholar 

  28. Rong HJ, Suresh S, Zhao GS. Stable indirect adaptive neural controller for a class of nonlinear system. Neurocomputing. 2011;74(16):2582–90.

    Article  Google Scholar 

  29. Saraswathi S, Sundaram S, Sundararajan N, Zimmermann M, Nilsen-Hamilton M. Icga-pso-elm approach for accurate multiclass cancer classification resulting in reduced gene sets in which genes encoding secreted proteins are highly represented. IEEE/ACM Trans Comput Biol Bioinform. 2011;8(2):452–63.

    Article  PubMed  Google Scholar 

  30. Suresh S, Sundararajan N, Saratchandran P. Risk-sensitive loss functions for sparse multi-category classification problems. Inf Sci. 2010;178(12):2621–38.

    Article  Google Scholar 

  31. Suresh S, Venkatesh Babu R, Kim HJ. No-reference image quality assessment using modified extreme learning machine classifier. Appl Soft Comput. 2006;9(2):541–52.

    Article  Google Scholar 

  32. Suresh S, Babu V, Sundararajan N. Image quality measurement using sparse extreme learning machine classifier. In: 9th International conference on control, automation, robotics and vision, 2006, ICARCV’06, art. no. 4150396, 2006.

  33. Suresh S, Omkar SN, Mani V, Guru Prakash TN. Lift coefficient prediction at high angle of attack using recurrent neural network. Aerosp Sci Technol. 2003;7(8):595–602.

    Article  Google Scholar 

  34. Savitha R, Suresh S, Sundararajan N. Fast learning fully complex-valued classifiers for real-valued classification problems. Lect Notes Comput Sci. 2011;6675(part 1):602–9.

  35. Savitha R, Suresh S, Sundararajan N. A fast learning complex-valued neural classifier for real-valued classification problems. In: Proceedings of the international joint conference on neural networks, art. no. 6033508; 2011:2243–9.

  36. Savitha R, Suresh S, Sundararajan N. Fast learning circular complex-valued extreme learning machine (cc-elm) for real-valued classification problems. Inf Sci. 2012;187(1):277–90.

    Article  Google Scholar 

  37. Savitha R, Suresh S, Kim HJ. A meta-cognitive learning algorithm for an extreme learning machine classifier. Cogn Comput. (in press) 2013. doi:10.1007/s12559-013-9223-2

  38. Sun YJ, Yuan Y, Wang G. An os-elm based distributed ensemble classification framework in p2p networks. Neurocomputing. 2011;74(16):2438–43.

    Article  Google Scholar 

  39. Taylor JG, Cutsuridis V, Hartley M, Althoefer K, Nanayakkara T, observational learning: basis, experimental results and models, and implications for robotics. Cogn Comput. (in Press), 2013.

  40. Babu RV, Suresh S, Makur A. Online adaptive radial basis function networks for robust object tracking. Comput Vis Image Understand. 2010;114(3):297–310.

    Article  Google Scholar 

  41. Blake C, Merz C. UCI repository of machine learning databases. Department of Information and Computer Sciences, University of California, Irvine; 1998. URL: http://archive.ics.uci.edu/ml/.

  42. Shi YQ, Chen C, Chen W. Markov process based approach to effective attacking jpeg steganography. Lect Notes Comput Sci. 2006;4437:249–64.

    Article  Google Scholar 

  43. Solanki K, Jacobsen N, Madhow U, Manjunath BS, Chandrasekaran S. Robust image-adaptive data hiding based on erasure and error correction. IEEE Trans Image Process. 2004;13(12):1627–39.

    Article  PubMed  Google Scholar 

  44. Solanki K, Sakar A, Manjunath BS. Yass: yet another steganographic scheme that resists blind steganalysis. Lect Notes Comput Sci. 2007;4567:16–31.

    Article  Google Scholar 

  45. Wang GR, Zhao Y, Wang D. A protein secondary structure prediction framework based on the extreme learning machine. Neurocomputing. 2008;72(1–3):262–8.

    Article  Google Scholar 

  46. Wang QF, Cambria E, Liu CL, Hussain A. Common sense knowledge for handwritten chinese recognition. Cogn Comput. 2013;5(2):234–42.

    Article  Google Scholar 

  47. Zhang R, Sachnev V, Kim HJ. Fast bch syndrome coding for steganography. Lect Notes Comput Sci. 2009;5806:48–58.

    Article  Google Scholar 

  48. Zhang T. Statistical behavior and consistency of classification methods based on convex risk minimization. Ann Stat. 2004;32(1):56–85.

    Article  CAS  Google Scholar 

Download references

Acknowledgments

This work was supported by Catholic University of Korea, Research Funds 2013, National Research Foundation of Korea, Grant #2011-0013695.

Author information

Authors and Affiliations

  1. Department of Information, Communication and Electronics Engineering, Catholic University of Korea, Bucheon, South Korea

    Vasily Sachnev

  2. School of Computer Engineering, Nanyang Technological University, Nanyang Avenue, Singapore, 639798, Singapore

    Savitha Ramasamy & Suresh Sundaram

  3. Center of Information Security Technologies, Korea University, Seoul, South Korea

    Hyoung Joong Kim & Hee Joon Hwang

Authors
  1. Vasily Sachnev
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Savitha Ramasamy
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Suresh Sundaram
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hyoung Joong Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Hee Joon Hwang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Vasily Sachnev.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sachnev, V., Ramasamy, S., Sundaram, S. et al. A Cognitive Ensemble of Extreme Learning Machines for Steganalysis Based on Risk-Sensitive Hinge Loss Function. Cogn Comput 7, 103–110 (2015). https://doi.org/10.1007/s12559-014-9268-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-014-9268-x

Keywords

Search

Navigation