Spatial rich model steganalysis feature normalization on random feature-subsets
- 252 Downloads
Spatial rich model (SRM) steganalysis feature is formed by high-order statistics collected from image noise residuals. These statistics are simply rescaled before machine learning. It is noted that SRM features of different cover images are very different. In this paper, we propose a feature normalization method based on random feature-subsets (NRS) for SRM. We randomly draw feature-subsets from SRM feature. Then these feature-subsets are normalized by using per-sample rescaling method to make the feature-subsets of different images have the same 1-norm (the sum of all elements). The proposed NRS method can adjust the feature distribution and increase the feature diversity. The normalized feature-subsets can achieve better detection performance and also can be used as a useful complement for the existing steganalysis features. Experimental results show that: (1) a small amount of normalized feature-subset supplement can obviously improve the detection performance of SRM feature; (2) under the same dimensionality, the proposed NRS version feature can achieve a better detection accuracy than that of original feature; (3) the proposed NRS method is applicable to projections of spatial rich model feature; (4) compared with steganalysis feature extraction, the computational time of NRS can be negligible.
KeywordsSteganalysis Co-occurrence Feature normalization Random feature-subsets
The authors would like to thank the Network Center of Anhui University of Technology (AHUT) for providing cloud services to support this work. This study was funded by National Natural Science Foundation of China (Grant Nos. 61302178, 61105020), Foundation for Major Program of Education Bureau of Anhui Province (Grant No. KJ2015ZD09) and Excellent Youth Foundation of Anhui University of Technology (Grant No. z10097).
Compliance with ethical standards
Conflict of interest
All the authors and the Network Center of Anhui University of Technology declare that they have no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
- Anthony TH, Li S (2015) Handbook of digital forensics of multimedia data and devices. IEEE Press, New YorkGoogle Scholar
- Arpit D, Zhou Y, Kota BU, Govindaraju V (2016) Normalization propagation: A parametric technique for removing internal covariate shift in deep networks. In: Proceedings of the 33 rd international conference on machine learning, vol 48. New York, NY, USAGoogle Scholar
- Bas P, Filler T, Pevný T (2011) Break our steganographic system—the ins and outs of organizing boss’. In: Filler T, Pevný T, Ker A, Craver S (eds) 13th international conference of information hiding, lecture notes in computer science, Prague, Czech Republic, vol 6958, pp 59–70Google Scholar
- Cogranne R, Sedighi V, Fridrich J, Pevn T (2015) Is ensemble classifier needed for steganalysis in high-dimensional feature spaces? In: IEEE international workshop on information forensics and security. Italy, Rome, pp 1–5Google Scholar
- Ester M, Kriegel H, Sander J, Xu X (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: Simoudis E, Han J, Fayyad U (eds) Kdd, vol 96. AAAI Press, Menlo Park, CA, pp 226–231Google Scholar
- Goljan M, Fridrich J, Cogranne R (2014) Rich model for steganalysis of color images. In: IEEE workshop on information forensic and security. Atlanta, GAGoogle Scholar
- Holub V, Fridrich J (2012) Designing steganographic distortion using directional filters. In: Fourth IEEE international workshop on information forensics and security. Tenerife, Spain, pp 234–239Google Scholar
- Holub V, Fridrich J (2013a) Digital image steganography using universal distortion. In: Puech W, Chaumont M, Dittmann J, Campisi P (eds) Proceedings of the first ACM workshop on Information hiding and multimedia security. France, Montpellier, pp 59–68Google Scholar
- Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: 32nd international conference on machine learning (ICML 2015), vol 1, pp 448–456Google Scholar
- Lyu S, Farid H (2002) Detecting hidden messages using higher order statistics and support vector machines. In: 5th international workshop on information hiding, Lecture notes in computer science, vol 2578, pp 340–354Google Scholar
- Maaløe L, Sønderby CK, Sønderby SK, Winther O (2016) Auxiliary deep generative models. In: Proceedings of the 33rd international conference on machine learning, vol 48. New York, NY, USAGoogle Scholar
- Mohammadi FG, Abadeh MS (2014) A new metaheuristic feature subset selection approach for image steganalysis. J Intell Fuzzy Syst 27(3):1445–1455Google Scholar
- Ng A (2011) Linear regression ii: feature scaling. http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=MachineLearning&video=03.1-LinearRegressionII-FeatureScaling&speed=100/. Accessed 8 Dec 2015
- Ng A, Ngiam J, Foo CY, Mai Y, Suen C (2013) Data preprocessing. http://ufldl.stanford.edu/wiki/index.php/Data_Preprocessing. Accessed 8 Dec 2015
- Raschka S (2015) Feature scaling and normalization. http://www.tuicool.com/articles/qYN3Yve. Accessed 22 Feb 2016
- Sønderby CK, Raiko T, Maaløe L, Sønderby SK, Winther O (2016) Ladder variational autoencoders. In: NIPS 2016: annual conference on neural information processing systems. Barcelona, SpainGoogle Scholar
- Song X, Liu F, Yang C, Luo X, Zhang Y (2015) Steganalysis of adaptive JPEG steganography using 2D Gabor filters. In: ACM workshop on information hiding and multimedia security, pp 15–23Google Scholar
- Zou D, Shi YQ, Su W, Xuan G (2006) Steganalysis based on markov model of thresholded prediction-error image. In: Proceedings of the IEEE international conference on multimedia and expo, Toronto, Canada, pp 1365–1368Google Scholar