Abstract
The threat posed by hackers, spies, terrorists, and criminals, etc. using steganography for stealthy communications and other illegal purposes is a serious concern of cyber security. Several steganographic systems that have been developed and made readily available utilize JPEG images as carriers. Due to the popularity of JPEG images on the Internet, effective steganalysis techniques are called for to counter the threat of JPEG steganography. In this article, we propose a new approach based on feature mining on the discrete cosine transform (DCT) domain and machine learning for steganalysis of JPEG images. First, neighboring joint density features on both intra-block and inter-block are extracted from the DCT coefficient array and the absolute array, respectively; then a support vector machine (SVM) is applied to the features for detection. An evolving neural-fuzzy inference system is employed to predict the hiding amount in JPEG steganograms. We also adopt a feature selection method of support vector machine recursive feature elimination to reduce the number of features. Experimental results show that, in detecting several JPEG-based steganographic systems, our method prominently outperforms the well-known Markov-process based approach.
- Avcibas, I., Memon, N., and Sankur, B. 2003. Steganalysis using image quality metrics. IEEE Trans. Image Proc. 12, 2, 221--229. Google ScholarDigital Library
- Chang, C., Lin, C., Tseng, C., and Tai, W. 2007. Reversible hiding in DCT-based compressed images. Inf. Sci. 177, 13, 2768--2786. Google ScholarDigital Library
- Chen, C. and Shi, Y. 2008. JPEG image steganalysis utilizing both intrablock and interblock correlations. In Proceedings of the IEEE International Symposium on Circuits and Systems. 3029--3032.Google Scholar
- Cho, D. and Bui, T. 2005. Multivariate statistical modeling for image denoising using wavelet transforms. Signal Process. Image Commun. 20, 1, 77--89.Google ScholarCross Ref
- Fridrich, J., Goljan, M., and Hogeam, D. 2002. Steganalysis of JPEG images: Breaking the F5 algorithm. In Proceedings of the 5th Information Hiding Workshop. 310--323. Google ScholarDigital Library
- Fridrich, J. 2004. Feature-based steganalysis for JPEG images and its implications for future design of steganographic schemes. Lecture Notes in Computer Science, vol. 3200, 67--81. Google ScholarDigital Library
- Guyon, I., Weston, J., Barnhill, S., and Vapnik, V. N. 2002. Gene selection for cancer classification using support vector machines. Mach. Learn., 46, 1-3, 389--422. Google ScholarDigital Library
- Harmsen, J. and Pearlman, W. 2003. Steganalysis of additive noise modelable information hiding. In Proceedings of the SPIE, vol. 5020, 131--142.Google Scholar
- Harmsen, J. and Pearlman, W. 2004. Kernel fisher discriminant for steganalysis of JPEG hiding methods. In Proceedings of the SPIE, vol. 5306, 13--22.Google Scholar
- Hetzl, S. and Mutzel, P. 2005. A graph-theoretic approach to steganography. Lecture Notes in Computer Science, vol. 3677, 119--128. Google ScholarDigital Library
- Joachims, T. 1999. Making large-scale SVM learning practical. In Advances in Kernel Methods—Support Vector Learning, B. Schölkopf, C. Burges and A. Smola, Eds., MIT Press. Google ScholarDigital Library
- Joachims, T. 2000. Estimating the generalization performance of a SVM efficiently. In Proceedings of the 7th International Conference on Machine Learning, Morgan Kaufman. Google ScholarDigital Library
- Joachims, T. 2002. Learning to Classify Text Using Support Vector Machines. Kluwer. Google ScholarDigital Library
- Kasabov, N. K. and Song, Q. 2002. DENFIS: Dynamic evolving neural-fuzzy inference system and its application for time-series. IEEE Trans. Fuzzy Syst. 10, 2, 144--154. Google ScholarDigital Library
- Katzenbeisser, S. and Petitcolas, F. 2000. Information Hiding Techniques for Steganography and Digital Watermarking. Artech House Books. Google ScholarDigital Library
- Ker, A. 2005. Improved detection of LSB steganography in grayscale images. Lecture Notes in Computer Science, vol. 3200, 97--115. Google ScholarDigital Library
- Kim, Y., Duric, Z., and Richards, D. 2006. Modified matrix encoding technique for minimal distortion stegangoraphy. In Proceedings of the 8th International Workshop on Information Hiding. Lecture Notes in Computer Science, vol. 4437, 314--327. Google ScholarDigital Library
- Kodovsky, J., Pevny, T., and Fridrich, J. 2010. Modern steganalysis can detect YASS. In Proceedings of the SPIE, Electronic Imaging, Media Forensics and Security XII, 02-01--02-11.Google Scholar
- Li, B., Shi, Y., and Huang, J. 2009. Steganalysis of YASS. IEEE Trans. Inf. Foren. Sec. 4, 3, 369--382. Google ScholarDigital Library
- Liu, Q. and Sung, A. H. 2007. Feature mining and nuero-fuzzy inference system for steganalysis of LSB matching steganography in grayscale images. In Proceedings of the 20th International Joint Conference on Artificial Intelligence. 2808--2813. Google ScholarDigital Library
- Liu, Q., Sung, A. H., Chen, H., and Xu, J. 2008a. Feature mining and pattern classification for steganalysis of LSB matching steganography in grayscale images. Patt. Recog. 41, 1, 56--66. Google ScholarDigital Library
- Liu, Q., Sung, A. H., Ribeiro, B. M., Wei, M., Chen, Z., and Xu, J. 2008b. Image complexity and feature mining for steganalysis of least significant bit matching steganography. Inf. Sci. 178, 1, 21--36. Google ScholarDigital Library
- Liu, Q., Sung, A. H., Ribeiro, B., and Ferriera, R. 2008c. Steganalysis of multi-class JPEG images based on expanded Markov features and polynomial fitting. In Proceedings of the 21st International Joint Conference on Neural Networks, 3351--3356.Google Scholar
- Liu, Q., Sung, A. H., and Qiao, M. 2009a. Temporal derivative-based spectrum and mel-cepstrum audio steganalysis. IEEE Trans. Inf. Foren. Sec. 4, 3, 359--368. Google ScholarDigital Library
- Liu, Q., Sung, A. H., and Qiao, M. 2009b. Novel stream mining for audio steganalysis. In Proceedings of the 17th ACM Conference on Multimedia. 95--104. Google ScholarDigital Library
- Liu, Q., Sung, A. H., and Qiao, M. 2009c. Improved detection and evaluation for JPEG steganalysis. In Proceedings of the 17th ACM Conference on Multimedia. 873--876. Google ScholarDigital Library
- Liu, Q. and Sung, A. H. 2009d. A new approach for JPEG resize and image splicing detection. In Proceedings of the ACM Multimedia Workshop on Multimedia Forensics. 43--47. Google ScholarDigital Library
- Liu, Q., Sung, A. H., Qiao, M., Chen, Z., and Ribeiro, B. 2010a. An improved approach to steganaysis of JPEG images. Inf. Sci. 180, 9, 1643--1655. Google ScholarDigital Library
- Liu, Q., Sung, A. H., and Qiao, M. 2010b. Derivative based audio steganalysis. ACM Trans. Multimed. Comput. Comm. Appl. To appear. Google ScholarDigital Library
- Lyu, S. and Farid, H. 2005. How realistic is photorealistic. IEEE Trans. Signal Proc. 53, 2, 845--850. Google ScholarDigital Library
- Marvel, L., Boncelet, C., and Retter, C. 1999. Spread spectrum image steganography. IEEE Trans. Image Proc. 8, 8, 1075--1083. Google ScholarDigital Library
- Mielikainen, J. 2006. LSB matching revisited. IEEE Sig. Proc. Lett. 13, 5, 285--287.Google ScholarCross Ref
- Ohm, J. R. 2004. Multimedia Communication Technology, Representation, Transmission and Identification of Multimedia Signals. Springer, Berlin.Google Scholar
- Pevny, T. and Fridrich, J. 2007. Merging Markov and DCT features for multi-class JPEG steganalysis. In Proceedings of the SPIE, vol. 6505, DOI: 10.1117/12.696774.Google Scholar
- Pevny, T., Filler, T., and Bas, P. 2010. Using high-dimensional image models to perform highly undetectable steganography. In Proceedings of the 12th International Workshop on Information Hiding. Lecture Notes in Computer Science, vol. 6387, 161--177. Google ScholarDigital Library
- Provos, N. 2001. Defending against statistical steganalysis. In Proceedings of the 10th USENIX Security Symposium. 323--335. Google ScholarDigital Library
- Sachnev, V., Kim, H. J., and Zhang, R. 2009. Less detectable JPEG steganography method based on heuristic optimization and BCH syndrome code. In Proceedings of the 11th ACM Multimedia & Security Workshop. 131--140. Google ScholarDigital Library
- Sallee, P. 2004. Model based steganography. Lecture Notes in Computer Science, vol. 2939, 154--167.Google ScholarCross Ref
- Sarkar, A., Nataraj, L., Manjunath, B. S., and Madhow, U. 2008a. Estimation of optimum coding redundancy and frequency domain analysis of attacks for YASS—A randomized block based hiding scheme. In Proceedings of the 15th IEEE International Conference on Image Processing. 1292--1295.Google Scholar
- Sarkar, A., Solanki, K., and Manjunath, B. S. 2008b. Further study on YASS: Steganography based on randomized embedding to resist blind steganalysis. In Proceedings of the SPIE—Security, Steganography, and Watermarking of Multimedia Contents (X), vol. 6819. DOI: 10.1117/12.767893.Google Scholar
- Sharifi, K. and Leon-Garcia, A. 1995. Estimation of shape parameter for generalized Gaussian distributions in subband decompositions of video. IEEE Trans. Circuits Syst. Video Technol. 5, 52--56. Google ScholarDigital Library
- Sharp, T. 2001. An implementation of key-based digital signal steganography. Lecture Notes in Computer Science, vol. 2137, 13--26. Google ScholarDigital Library
- Shi, Y., Chen, C., and Chen, W. 2007. A Markov process based approach to effective attacking JPEG steganography. Lecture Notes in Computer Science, vol. 4437, 249--264. Google ScholarDigital Library
- Solanki, K., Sarkar, A., and Manjunath, B. 2007. YASS: Yet another steganogrpahic scheme that resists blind steganalysis. Lecture Notes in Computer Science, vol. 4567, 16--31. Google ScholarDigital Library
- Vapnik, V. 1998. Statistical Learning Theory, Wiley.Google Scholar
- Westfeld, A. 2001. High capacity despite better steganalysis (F5—a steganographic algorithm). Lecture Notes in Computer Science, vol. 2137, 289--302. Google ScholarDigital Library
- Yu, X. and Babaguchi, N. 2008. Breaking the YASS algorithm via pixel and DCT coefficients analysis. In Proceedings of the 19th International Conference on Pattern Recognition. 1--4.Google Scholar
Index Terms
- Neighboring joint density-based JPEG steganalysis
Recommendations
Steganalysis of DCT-embedding based adaptive steganography and YASS
MM&Sec '11: Proceedings of the thirteenth ACM multimedia workshop on Multimedia and securityRecently well-designed adaptive steganographic systems, including ±1 embedding in the DCT domain with optimized costs to achieve the minimal-distortion [8], have posed serious challenges to steganalyzers. Additionally, although the steganalysis of Yet ...
Improved Approaches with Calibrated Neighboring Joint Density to Steganalysis and Seam-Carved Forgery Detection in JPEG Images
Special Sections on Diversity and Discovery in Recommender Systems, Online Advertising and Regular PapersSteganalysis and forgery detection in image forensics are generally investigated separately. We have designed a method targeting the detection of both steganography and seam-carved forgery in JPEG images. We analyze the neighboring joint density of the ...
A JPEG-based statistically invisible steganography
ICIMCS '11: Proceedings of the Third International Conference on Internet Multimedia Computing and ServiceThe objective of steganography is to implement covert communication by hiding data in digital files such that there is no indication of the existence of hidden data; so an ideal steganographic system should be able to withstand all steganalysis methods--...
Comments