An Efficient JPEG Steganographic Scheme Design Using Domain Transformation of Embedding Cost

08/06/2019 ∙ by Wenkang Su, et al. ∙ 0

Although the recently proposed JPEG steganography using Block embedding Entropy Transformation scheme (BET) shows excellent security performance, its procedure is much complicate. In this paper, we intend to introduce a Block embedding Cost Transformation (BCT) scheme for JPEG steganography. The core of our proposed BCT is the embedding cost domain transformation function, which comprises of the proposed distinguish factors of inter-block and intra-block, i.e., spatial (pixel) block embedding costs and spatial (pixel) block embedding changes, respectively. And moreover, for further maintaining the statistical undetectability of the stego, an exponential model is then introduced to facilitate the construction of domain transformation function. With the aid of the proposed domain transformation function, the JPEG embedding cost can be easily obtained through weighting the spatial embedding costs by the spatial embedding changes. In this way, the design procedure of JPEG steganographic distortion function under BCT will be more simplified than BET, and following this paradigm, the spatial image steganography will be more meaningful as well. Experimental results show that the proposed BCT has a more comprehensive performance improvement than UERD with the same computational complexity, and is superior to J-UNIWARD and GUED in resisting the detection of GFR and SCA-GFR. In addition, it can also rival BET with an order of magnitude lower computational complexity.

READ FULL TEXT VIEW PDF
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.

I Introduction

Steganography is the science and art of covert communication without drawing suspicion from Warden [1]. With the rapid development of multimedia information technology, the image steganography technology and its applications [2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12] have also made great progress in the past decade. And among them, the content-adaptive JPEG image steganography is the most effective and practical one which conceals secret messages in quantized DCT coefficients.

With the emergence of breakthrough coding method–STCs (Syndrome-Trellis Codes) [8], all the prevailing JPEG steganographic schemes are focused on the design of effective distortion function. Recalling the development of JPEG steganography in the past decade, it is observed that the mainstream design scheme for JPEG steganographic distortion function (additive distortion function), e.g., J-UNIWARD [11], UERD [12], BET [7], GUED [6] and etc., can be summarized as the framework that =, where is the Intra-block distinguish Factor which indicates intra-block embedding costs for different modes, and is the Inter-block distinguish Factor which suggests inter-block embedding costs for different DCT blocks. The value of embedding cost determines the level of embedding priority, that is, smaller embedding cost will arise higher embedding priority, and vice versa. Based on this framework, numerous researchers have devoted themselves to designing better and .

In terms of the design for , all the mentioned steganographic distortion function adopt the quantization table (or its derivant) of JPEG cover. As far as the design for , it is the most striking difference among them, which can be summarized into two categories, i.e., design from DCT domain and design from spatial domain. For the first category, UERD is the typical one which adopts the block energy, i.e., the sum of the absolute value of dequantized DCT coefficient within the DCT block. However, this category method does not take into account the changes of spatial domain statistical characteristics after embedding, which can be easily detected by the JPEG phase feature sets based steganalyzers, e.g., DCTR [13] and GFR [14]. In view of this defect, the second category method that design from spatial domain came into being, such as J-UNIWARD, GUED, BET and etc.. The J-UNIWARD constructs utilizing the wavelet residuals obtained by filtering the decompressed cover using the Daubechies 8-tap wavelet directional filter bank, and similarly, GUED designs

based on the Gabor residuals. Peculiarly, BET uses a domain transformation of embedding entropy scheme that transforms the block embedding entropy of the spatial domain into DCT domain, and then derives the JPEG embedding change probability based on a white noise embedding assumption, afterwards the corresponding

, i.e., JPEG block embedding cost, can be conversely derived according to the method in [15]. Experimental results show that BET is superior to UERD and J-UNIWARD in resisting the detection of GFR. However, the fly in the ointment is that the procedure of BET is so complicate, including two rounds transformation for distortion cost, modification probability and entropy, which will limit its practical applicability.

Motivated by the defect of BET, this paper proposes a domain transformation of embedding cost scheme. In contrast with BET, the proposed scheme no longer needs to calculate the mediums in the construction of distortion function of BET, i.e., embedding modification probability and embedding entropy, and instead, a embedding cost domain transformation function is introduced to directly transform the spatial embedding cost into JPEG domain by means of a linear weighted method. The proposed f comprises of the distinguish factors of intra-block and inter-block , which are the pixel block embedding changes and the pixel block embedding cost, respectively. In order to further maintain the statistical undetectability of the stego in both DCT and spatial domains, an exponential model is then introduced to facilitate the construction of in terms of . Extensive experiments show that the proposed scheme has a more comprehensive performance improvement than UERD with the same computational complexity, and is superior to JUNIWARD and GUED in resisting the detection of GFR and SCA-GFR [16]. Besides, it also rivals BET with an order of magnitude lower computational complexity.

The remainder of this paper is organized as follows. In the next Section, we mainly introduce the construction of embedding cost domain transformation function, which are followed by the experimental results and analysis in Section III. Finally, the paper is concluded in Section IV.

Ii The proposed block embedding cost transformation scheme

Ii-a The new inter-block distinguish factor

As we know, the essence of and are to distinguish the embedding priorities of different DCT blocks and differentDCT modes within the same DCT block, respectively. Specifically, the smaller the value of distinguish factor is, the higher the corresponding embedding priority will be, and vice versa. In addition, the difference in security performance among different JPEG steganographic schemes under the same framework of minimal distortion embedding is due to the difference on the selection of DCT coefficients for embedding. Therefore, the following consensus can be easily obtained: 1) if the distinguish factors designed by different schemes have a high degree of similarity in evaluating the embedding priority, then they will be in the similar embedding security level, and vice versa, and 2) if the embedding security level of a steganographic scheme is higher, then the evaluation of embedding priority by this scheme will be more reasonable, and vice versa.

In our proposed scheme, we intend to replace the block embedding entropy in BET with pixel block embedding cost of the decompressed cover, which is referred to as the new Inter-block distinguish Factor (). With regard to the method of calculating the spatial embedding cost, there are many choices, such as S-UNIWARD [11], Hill [9], MiPOD [15] and etc.. While, to the best of our knowledge, the Hill may be the best one, due to its excellent security performance and minimal computational complexity 111We also test other spatial steganographic algorithms in BCT, while they are all inferior to Hill, which ulteriorly verifies the above consensus.. To verify the feasibility of the proposed in evaluating the DCT block embedding priority, we then make a simple experiment in the following.

Without loss of generality, we randomly select 2000 cover images from BOSSbaseJ75 and BOSSbaseJ95222Compress the images in BOSSbase ver1.01 [17] using JPEG Toolbox [18] with =75 and =95. separately, and then use UERD, J-UNIWARD, GUED and Hill to calculate the embedding cost of each (DCT or pixel) block within each cover. It should be noted in this experiment that the block embedding cost under Hill is expressed by the sum of 64 pixels’ embedding costs within this block, while for J-UNIWARD, the block embedding cost is expressed by the reciprocal sum of absolute value of wavelet filter residuals in three directions corresponding to this block. As referred before, the embedding priority is determined by the embedding cost, thus, the similarity of block embedding priority among different steganographic schemes can be indirectly obtained by calculating the similarity of their block embedding costs. As far as the choice of metric for similarity, we adopt the Spearman Correlation Coefficient (SCC) [19], which is one of the three popular statistical correlation coefficients, corresponding to the ‘corr’ Matlab command with type ‘Spearman’. The magnitude represents the degree of correlation (0 is irrelevant, 1 is completely linear relevant). Finally, the average Spearman Correlation Coefficients (SCCs) over 2000 cover images for Q75 and Q95 are summarized in Table I.

Different schemes Q75 Q95
SCC(UERD,Hill)
SCC(J-UNIWARD,Hill)
SCC(GUED,Hill)
TABLE I: The average Spearman Correlation Coefficients (SCCs) of block embedding priority for Q75 and Q95 between UERD, J-UNIWARD, GUED and Hill, respectively.

Comparing the results of UERD with J-UNIWARD, it is observed that J-UNIWARD is closer to Hill than UERD in evaluating the block embedding priority along with higher security performance towards effective steganalyzer GFR. And similar situation also occurs in J-UNIWARD and GUED. Furthermore, referring to the performance in BET [7] and GUED [6], it is then observed that BET-Hill is superior to GUED in resisting the detection of GFR, where the of BET-Hill (i.e., pixel block embedding entropy) is obtained by Hill. In this regard, it is convinced that if the evaluation of block embedding priority of a JPEG steganographic scheme is closer to Hill’s, then it would be more secure. Go for a step further, if we directly choose the block embedding cost calculated by Hill to evaluate the DCT block embedding priority, then it would yield optimal security performance in this case. Of course, if there are some other better spatial steganographic algorithms can substitute Hill, we believe that the similar conclusions will also be obtained as discussed with regard to Hill.

Ii-B The new intra-block distinguish factor

It is well known that when we arbitrarily modify a DCT coefficient (mode () in the () DCT block) in JPEG cover image, the corresponding spatial embedding changes can be easily derived by its inverse DCT transformation. Since JPEG compression is based on block DCT transformation, then the corresponding spatial embedding changes will just occur within its corresponding pixel block, which is only associated with its quantization step . In this way, the relationship between the DCT domain embedding modification and the spatial embedding changes can be expressed as:

(1)

where represents the solitary modification on mode , and demonstrates the resultant corresponding spatial pixel block embedding changes, which is referred to as the new Intra-block distinguish Factor ().

Ii-C The construction of the proposed embedding cost domain transformation function

Since the proposed new is made to be the pixel block embedding costs, and is represented by the corresponding pixel block embedding changes when modifying each DCT mode, thereby, we consider it as a matter of course to use the to perform a linear weighted operation on the , and then accumulate the weighted results to obtain the JPEG embedding costs. Therefore, the proposed scheme can be referred to as Block embedding Cost Transformation (BCT) scheme, and the corresponding embedding cost domain transformation function is represented as:

(2)

where represents the embedding cost of the pixel in the spatial block when modified by magnitude 1, indicates the resultant spatial embedding change magnitude of the pixel in the corresponding spatial block when modifying mode by magnitude 1, and is the JPEG embedding cost of mode in the DCT block.

It is noted that the spatial adaptive steganographic schemes, e.g., S-UNIWARD, Hill, MiPOD and etc., are all prone to embed messages in texture regions of the cover, i.e., mid-to-high frequency regions of the cover. Therefore, the proposed BCT-Hill scheme will have a tendency to modify more mid-to-high frequency DCT coefficients in JPEG cover for data embedding. In other words, the proposed BCT-Hill scheme will migrate a part of embedding modifications to mid-to-high frequency DCT coefficients of complex DCT block, so as to weaken the change of spatial statistical characteristics of cover as far as possible, while it should be moderate, otherwise terrible spatial embedding changes would be yielded, especially at small QFs. As thus, how to control the number of migration of embedding modifications will become an urgent problem to be solved. Since the in the proposed is totally determined by the quantization table, that the embedding priority of the low-frequency mode is naturally higher than the one of the high-frequency mode, thus we can only anchor our hope on the proposed . As the proposed is constructed by the spatial block embedding costs , and we find that by reducing the relative magnitude of d in mid-to-high frequency region, much more messages would be prone to be embedded in the corresponding DCT block, thereby increasing the number of modifications on the mid-to-high frequency modes, and vice versa. In this regard, we then make the spatial embedding cost as the exponential form with parameter , and by which we desire to adjust flexibly the relative magnitude of , thus the proposed can be rewritten as:

(3)

Iii Experimental results and analysis

Iii-a Experiment setups

All the experiments in this Section are carried out on the image dataset BOSSbase ver1.01 [17] at =75 and =95, and for each, one half of them are used for training, while others for testing. Several state-of-the-art universal and typical JPEG steganalyzers, including CC-JRM-22,510D [20], GFR-17,000D [14], and the selection-channel-aware version of GFR (SCA-GFR-17,000D [16]

), are employed to evaluate the empirical security performance of the tested JPEG steganographic schemes, where the binary classifier is trained by the Fisher Linear Discriminants (FLD) ensemble

[21] with default settings. The classification error probability of FLD ensemble classifier, corresponding to the empirical security performance of the tested JPEG steganographic scheme, is reported by the mean value of the ensemble’s testing errors based on ten times of randomly testing and all the experiments are simulated at the corresponding payload distortion bound for relative payloads bpnzAC.

Iii-B Determining the optimal in BCT-Hill

Since the parameter in the exponential model can adjust the migration of embedding changes to the mid-to-high frequency DCT coefficients, thus there should be an optimal setting for given steganalyzer, and relative payload. To determine the optimal , we randomly select 5,000 images with given , and of these 2,500 JPEG images are used for training, while others for testing. We set in range of [0.3,1.5] with step 0.1, and then intentionally search on this interval to find the corresponding to the maximum classification error probability at given relative payload for each of the three tested steganalyzers. Finally, the optimal parameters for =75 and =95 are summarized in Table II, which are irrespective of relative payloads.

optimal Steganalyzer
CC-JRM GFR SCA-GFR
Q75
Q95
TABLE II: The optimal parameters of BCT-Hill for all the tested steganalyzers CC-JRM-22510D, GFR-17000D and SCA-GFR-17000D on BOSSbaseJ75 and BOSSbaseJ95.

Iii-C Security performance comparison and analysis

We then compare the security performance of the proposed BCT-Hill with UERD, J-UNIWARD, GUED and BET-Hill under different relative payloads and on BOSSbaseJ75 and BOSSbaseJ95, which are summarized in Table III and IV, respectively. For brevity, all the data (except BCT-Hill-pro) in Table III and IV are obtained under the optimal parameter setting for SCA-GFR (i.e., =0.5 and =0.9 for Q75 and Q95, respectively.). This is because SCA-GFR is the most effective steganalyzer and the performance of the proposed BCT-Hill won’t vary much for other steganalyzers, as has been validated by our experiments.

Referring to the results in Table III and IV, it is observed that under the detection of SCA-GFR-17000D, the proposed BCT-Hill shows an overall superior performance than UERD, J-UNIWARD and GUED. In addition, BCT-Hill also consistently outperforms BET-Hill by a clear margin (improvements can reach 1.4%-2.1% on average) under =75, and rivals BET-Hill under =95.

While for the detection of steganalyzer GFR, the situation is slightly different. Although our proposed BCT-Hill shows excellent security performance compared with the other tested schemes under =95, it doesn’t perform equally well under =75. We analyse that it may be due to the following reasons. The first is the suboptimal parameter setting for GFR. We then simulate BCT-Hill under the optimal parameter setting for GFR under =75 (i.e., =0.7), and the security performance is indeed improved as illustrated in Table III (BCT-Hill-pro). The second may be the intuitive consideration in Eq. (3) that the spatial embedding distortion cost increase linearly with the magnitude of pixel embedding change.

Steganalyzer Scheme Relative payload (bpnzAC)
0.1 0.2 0.3 0.4 0.5
CC-JRM UERD
J-UNIWARD
GUED
BET-Hill
BCT-Hill
BCT-Hill-pro 46.62 40.10 32.25 24.10 17.02
GFR UERD
J-UNIWARD
GUED
BET-Hill
BCT-Hill
BCT-Hill-pro 41.30 29.90 19.61 12.06 6.80
SCA-GFR UERD
J-UNIWARD
GUED
BET-Hill
BCT-Hill
TABLE III: Classification error probability (in %) of the tested JPEG steganographic schemes for CC-JRM, GFR and SCA-GFR versus relative payloads on BOSSbaseJ75.
Steganalyzer Scheme Relative payload (bpnzAC)
0.1 0.2 0.3 0.4 0.5
CC-JRM UERD
J-UNIWARD
GUED
BET-Hill
BCT-Hill
GFR UERD
J-UNIWARD
GUED
BET-Hill
BCT-Hill
SCA-GFR UERD
J-UNIWARD
GUED
BET-Hill
BCT-Hill
TABLE IV: Classification error probability (in %) of the tested JPEG steganographic schemes for CC-JRM-22510D, GFR-17000D and SCA-GFR-17000D versus relative payloads on BOSSbaseJ95.

In particular, the situation is dramatically different for the detection of CC-JRM that both BCT-Hill and BET-Hill are inferior to J-UNIWARD and GUED. We infer that it may be due to the more embedding modifications on mid-to-high frequency modes than J-UNIWARD and GUED, which would make the embedding traces in BCT-Hill and BET-Hill be exposed easier to steganalyzer CC-JRM. To validate this inference, we remove the integral components of CC-JRM, which are sensitive to the changes of the statistics of mid-to-high frequency modes, and the resultant feature set is denoted as crop-CC-JRM. Immediately, applying the crop-CC-JRM-17,270D to detect J-UNIWARD, GUED, BET-Hill and BCT-Hill at 0.4 bpnzAC under =75 and =95, and the comparison results are collected in Table V. It shows that the security performance improvements of the proposed BCT-Hill can reach 2.42% and 2.85% at =75 and =95, respectively. And a similar circumstance also happens in BET-Hill. While for J-UNIWARD and GUED, the improvements are marginal. Besides, similar to GFR, we then simulate BCT-Hill under the optimal parameter setting for CC-JRM under =75 (i.e., =0.7), and the results show that although the security performance of BCT-Hill has been improved, as shown in Table III (BCT-Hill-pro), it still inferior to J-UNIWARD and GUED by a clear margin. To this end, an important remark can be drawn from these results: if we improve the JPEG steganography performance on resisting the detection of JPEG steganalyzers derived from spatial domain (e.g., GFR) through migrating the embedding modifications to mid-to-high frequency DCT coefficients, then the risk of being detected by the steganalyzers derived from DCT domain (e.g., CC-JRM) is likely to increase.

As a supplementary, we ulteriorly test the applicability of our proposed scheme for other datasets (other image dataset and QFs), and the results show that it is also applicable. Due to the limitation of paper length, we can not give out the specific experimental results here.

Scheme CC-JRM crop-CC-JRM
Q75 Q95 Q75 Q95 Q75 Q95
J-UNIWARD
GUED
BET-Hill
BCT-Hill
TABLE V: Classification error probability (in %) of J-UNIWARD, GUED, BET-Hill and BCT-Hill for CC-JRM and crop-CC-JRM at 0.4 bpnzAC under =75 and =95. ( is the difference of between crop-CC-JRM and CC-JRM.)

Iii-D Practical evaluation of computational complexity

For this subsection, we aim at further evaluating the cost of our proposed BCT-Hill compared to UERD, J-UNIWARD, GUED and BET-Hill in terms of computation time (CmpTime). Note that all the tested steganographic schemes are simulated under the same framework of minimal distortion embedding, thereby the main difference among them is the their distortion functions, so we only choose to test their practical computation times in calculation of distortion costs.

In our implementation, we calculate the average CmpTimes of the distortion costs for UERD, J-UNIWARD, GUED, BET-Hill and BCT-Hill, over 2,000 JPEG images randomly selected from BOSSbaseJ75 and BOSSbaseJ95, respectively, using MATLAB 8.2 on a 3.0 GHz Intel Core i5-7400 CPU with 8GB memory. Finally, the results are listed in Table VI. It is observed that: 1) the CmpTime of BCT-Hill is greatly reduced than BET-Hill, GUED and J-UNIWARD; 2) the computation of BCT-Hill could be implemented in a quite affordable time cost as little as UERD.

Average time consuming (s)
UERD J-UNIWARD GUED BET-Hill BCT-Hill
Q75
Q95
TABLE VI: Average CmpTimes over 2,000 JPEG images of bits under =75 and =95 in calculation of distortion costs for UERD, J-UNIWARD, GUED, BET-Hill (0.4bpnzAC) and BCT-Hill. The unit of time is second (s).

Iv Conclusion

In this paper, a new JPEG steganographic scheme BCT-Hill using domain transformation of embedding cost is presented. The proposed BCT-Hill intends to transform the spatial block embedding cost in alignment with the DCT block into DCT domain by incorporating the proposed embedding cost domain transformation function . The proposed consists of the new proposed intra-block distinguish factor and inter-block distinguish factor , which are obtained via the pixel block embedding changes and the pixel block embedding costs, respectively. For further maintaining the statistical undetectability of the stego, an exponential model is then introduced to facilitate the construction of in terms of . As for the determination of the parameter of exponential model, we search on a given interval to find the optimal which yields the maximum classification error probability for different and JPEG steganalyzers. Extensive experiments are carried out, which demonstrate that the proposed scheme has a more comprehensive performance improvement than UERD with the same computational complexity, and is superior to J-UNIWARD and GUED in resisting the detection of GFR and SCA-GFR. Moreover, the proposed scheme can rival BET-Hill with an order of magnitude lower computational complexity as well. Although the BET-Hill and BCT-Hill are inferior to J-UNIWARD and GUED on resisting the detection of CC-JRM, it gives us an important remark w.r.t JPEG steganography, as shown in Section III-C. Incidentally, our proposed scheme broadens the application of spatial steganography, and by this way, not only the security of JPEG steganography would be improved based on a better spatial distortion function, but also the research of spatial steganography will become more meaningful.

References

  • [1] K. D, “The history of steganography,” in Anderson R. (eds) Information Hiding. IH 1996. LNCS, vol. 1174.   Springer, Berlin, Heidelberg, 1996, pp. 1–5.
  • [2] J. Tao, S. Li, X. Zhang, and Z. Wang, “Towards robust image steganography,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 29, no. 2, pp. 594–600, 2019.
  • [3] Y. Zhang, X. Luo, Y. Guo, C. Qin, and F. Liu, “Multiple robustness enhancements for image adaptive steganography in lossy channels,” IEEE Transactions on Circuits and Systems for Video Technology, 2019, early Access.
  • [4]

    W. Li, K. Chen, W. Zhang, H. Zhou, Y. Wang, and N. Yu, “Jpeg steganography with estimated side-information,”

    IEEE Transactions on Circuits and Systems for Video Technology, 2019, early Access.
  • [5] W. Zhang, Z. Zhang, L. Zhang, H. Li, and N. Yu, “Decomposing joint distortion for adaptive steganography,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 27, no. 10, pp. 2274–2280, 2017.
  • [6] W. Su, J. Ni, X. Li, and Y. Q. Shi, “A new distortion function design for jpeg steganography using the generalized uniform embedding strategy,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 28, no. 12, pp. 3545–3549, 2018.
  • [7] X. Hu, J. Ni, and Y. Q. Shi, “Efficient jpeg steganography using domain transformation of embedding entropy,” IEEE Signal Processing Letters, vol. 25, no. 6, pp. 773––777, 2018.
  • [8] T. Filler, J. Judas, and J. Fridrich, “Minimizing additive distortion in steganography using syndrome-trellis codes,” IEEE Transactions on Information Forensics and Security, vol. 6, no. 3, pp. 920–935, 2011.
  • [9] B. Li, M. Wang, J. Huang, and X. Li, “A new cost function for spatial image steganography,” in Proc. IEEE International Conference on Image Processing, 2014, pp. 4206–4210.
  • [10] L. Guo, J. Ni, and Y. Q. Shi, “Uniform embedding for efficient JPEG steganography,” IEEE Transactions on Information Forensics and Security, vol. 9, no. 5, pp. 814–825, 2014.
  • [11] V. Holub, J. Fridrich, and T. Denemark, “Universal distortion function for steganography in an arbitrary domain,” EURASIP Journal on Information Security, vol. 2014, no. 1, pp. 1–13, 2014.
  • [12] L. Guo, J. Ni, W. Su, C. Tang, and Y. Q. Shi, “Using statistical image model for JPEG steganography: Uniform embedding revisited,” IEEE Transactions on Information Forensics and Security, vol. 10, no. 12, pp. 2669–2680, 2015.
  • [13] V. Holub and J. Fridrich, “Low-complexity features for JPEG steganalysis using undecimated DCT,” IEEE Transactions on Information Forensics and Security, vol. 10, no. 2, pp. 219–228, 2015.
  • [14] X. Song, F. Liu, C. Yang, X. Luo, and Y. Zhang, “Steganalysis of adaptive JPEG steganography using 2D Gabor filters,” in Proc. 3rd ACM Workshop on Information Hiding and Multimedia Security, 2015, pp. 15–23.
  • [15] V. Sedighi, R. Cogranne, and J. Fridrich, “Content-adaptive steganography by minimizing statistical detectability,” IEEE Transactions on Information Forensics and Security, vol. 11, no. 2, pp. 221–234, 2016.
  • [16] T. Denemark, M. Boroumand, and J. Fridrich, “Steganalysis features for content-adaptive JPEG steganography,” IEEE Transactions on Information Forensics and Security, vol. 11, no. 8, pp. 1736–1746, 2016.
  • [17] P. Bas, T. Filler, and T. Pevný, “Break our steganographic system: the ins and outs of organizing BOSS,” in Filler T., Pevný T., Craver S., Ker A. (eds) Information Hiding. IH 2011. LNCS, vol. 6958.   Springer, Berlin, Heidelberg, 2011, pp. 59–70.
  • [18] “Phil sallee’s matlab jpeg toolbox.” [Online]. Available: http://dde.binghamton.edu/download/stegoalgorithms/.
  • [19] J. L. Myers and A. D. Well, Research Design and Statistical Analysis (2nd ed.).   Lawrence Erlbaum Associates, 2003.
  • [20] J. Kodovský and J. Fridrich, “Steganalysis of JPEG images using rich models,” in Proc. SPIE, Electronic Imaging, Media Watermarking, Security, and Forensics XIV, vol. 8303, 2012, pp. 0A 1–13.
  • [21] J. Kodovský, J. Fridrich, and V. Holub, “Ensemble classifiers for steganalysis of digital media,” IEEE Transactions on Information Forensics and Security, vol. 7, no. 2, pp. 432–444, 2012.