The International Arab Journal of Information Technology (IAJIT)


Low Dimensional Multi Class Steganalysis of Spatial LSB based Stego Images Using Textural Features

Image steganalysis ranges from detecting the presence of covert information in an image (passive steganalysis) to extraction of the information from the stego image (active steganalysis). One of the steps in active steganalysis is determining the stego algorithm used to produce the stego image. In this paper, a low dimensional combination of textural features is adapted for steganalysis. Also a novel blind statistical steganalyser to determine the spatial domain Least Significant Bit (LSB) based algorithms using one against one multi class classification is proposed. The proposed steganalyser is a multiclass ensemble Fisher Linear Discriminant (FLD) classifier that uses novel low dimensional textural features for steganalysis. The performed experiments on the Bossbase database for 5 different LSB based algorithms for 8 different payloads show that the results are much better than the state of art steganalyser.

[1] Arivazhagan S., Amrutha E., Jebarani W., and Veena S., “Hybrid Convolutional Neural Network Architecture Driven by Residual Features for Steganalysis of Spatial Steganographic Algorithms,” Neural Computing and Applications, vol. 33, no. 17, pp. 11465-11485, 2021.

[2] Arivazhagan S., Jebarani W., Veena S., and Amrutha E., “Extraction of Secrets from LSB Stego Images Using Various Denoising Methods,” The International Journal of Information Technology, vol. 15, pp. 2107-2121, 2023.

[3] Bas P., Filler T., and Pevný T., “Break our Steganographic System”: The Ins and Outs of Organizing BOSS,” in Proceedings of the Information Hiding 13th International Conference, Prague, pp. 59-70, 2011.

[4] Bogacsovics G., Toth J., Hajdu A., and Harangi B., “Enhancing CNNs through the Use of Hand- Crafted Features in Automated Fundus Image Classification,” Biomedical Signal Processing and Control, vol. 76, pp. 103685, 2022.

[5] Chen J., Lu W., Fang Y., Liu X., and Yeung Y., “Binary Image Steganalysis Based on Local Texture Pattern,” Journal of Visual Communication and Image Representation, vol. 55, pp. 149-56, 2018.

[6] Feng G., Zhang X., Ren Y., Qian Z., and Li S., “Diversity-Based Cascade Filters for JPEG Steganalysis,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 30, no. 2, pp. 376-86, 2020. doi: 10.1109/TCSVT.2019.2891778

[7] Figueroa A., “Refining Fine-Tuned Transformers with Hand-Crafted Features for Gender Screening on Question-Answering Communities,” Information Fusion, vol. 92, pp. 256-67, 2023.

[8] Frank E., Hall M., and Witten I., The WEKA Workbench Online Appendix for Data Mining Practical Machine Learning Tools and Techniques, Morgan Kaufman, 2016. al_2016_appendix.pdf

[9] Fridrich J. and Kodovsky J., “Rich Models for Steganalysis of Digital Images,” IEEE Transactions on Information Forensics and Low Dimensional Multi Class Steganalysis of Spatial LSB based Stego Images Using ... 241 Security, vol. 7, no. 3, pp. 868-882, 2012. doi: 10.1109/TIFS.2012.2190402

[10] Gul G. and Kurugollu F., “JPEG Image Steganalysis Using Multivariate PDF Estimates with MRF Cliques,” IEEE Transactions on Information Forensics and Security, vol. 8, no. 3, pp. 578-87, 2013. doi:10.1109/TIFS.2013.2247399

[11] Holub V., Fridrich J., and Denemark T., “Random Projections of Residuals as an Alternative to Co- Occurrences in Steganalysis,” IEEE Transactions on Information Forensics and Security, vol. 8, no. 12, pp. 1996, 2013. DOI:10.1109/TIFS.2013.2286682

[12] James G., Witten D., Hastie T., and Tibshirani R., An Introduction to Statistical Learning with Applications, Springer New York, 2021. 7138-7

[13] Jin Z., Feng G., Ren Y., and Zhang X., “Feature Extraction Optimization of JPEG Steganalysis Based on Residual Images,” Signal Processing, vol. 170, pp. 107455, 2020. righ

[14] Johnson N. and Jajodia S., “Exploring Steganography: Seeing the Unseen,” Computer, vol. 31, no. 2, pp. 26-34, 1998. doi: 10.1109/MC.1998.4655281

[15] Ker A., “Steganalysis of Embedding in Two Least- Significant Bits,” IEEE Transactions on Information Forensics and Security, vol. 2, no. 1, pp. 46-54, 2007. DOI:10.1109/TIFS.2006.890519

[16] Kodovsky J., Fridrich J., and Holub V., “Ensemble Classifiers for Steganalysis of Digital Media,” IEEE Transactions on Information Forensics and Security, vol. 7, no. 2, pp. 432-44, 2012. doi:10.1109/TIFS.2011.2175919

[17] Kuhn M. and Johnson K., “Over-Fitting and Model Tuning,” Applied Predictive Modeling, Springer, 2013.

[18] Lubenko I. and Ker A., “Steganalysis Using Logistic Regression,” Media Watermarking Security and Forensics III, vol. 7880, pp. 193-203 2011.

[19] Luo W., Dang J., Wang W., and Zhai F., “Low- Complexity JPEG Steganalysis Via Filters Optimation from Symmetric Property,” Multimedia Systems, vol. 27, no. 3, pp. 371-377, 2021.

[20] Mielikainen J., “LSB Matching Revisited,” IEEE Signal Processing Letters, vol. 13, no. 5, pp. 285- 287, 2006. doi: 10.1109/LSP.2006.870357

[21] Muralidharan T., Cohen A., Cohen A., and Nissim N., “The Infinite Race between Steganography and Steganalysis in Images,” Signal Processing, vol. 201, pp. 108711, 2022.

[22] Nouisser A., Zouari R., and Kherallah M., “Deep Learning Based MobileNet and Multi-Head Attention Model for Facial Expression Recognition,” The International Arab Journal of Information Technology, vol. 20, no. 3A, 2023.

[23] Pevny T., Bas P., and Fridrich J., “Steganalysis by Subtractive Pixel Adjacency Matrix,” IEEE Transactions on Information Forensics and Security, vol. 5, no. 2, pp. 215-224, 2010. doi:10.1109/TIFS.2010.2045842

[24] Pevný T. and Fridrich J., “Towards Multi-Class Blind Steganalyzer for JPEG Images,” The International workshop on Digital Watermarking, vol. 3710, pp. 39-53, 2005.

[25] Pevný T. and Fridrich J., “Multi-Class Blind Steganalysis for JPEG Images,” Security, Steganography, and Watermarking of Multimedia Contents VIII, vol. 6072. pp. 257-269, 2006.

[26] Priyadharshini R., Arivazhagan S., and Arun M., “Crack Recognition on Concrete Structures Based on Machine Crafted and Hand Crafted Features,” Expert Systems with Applications, vol. 228, pp. 120447, 2023.

[27] Sharp T., “An Implementation of Key-Based Digital Signal Steganography,” The International Workshop on Information Hiding. pp. 13-26, 2001. DOI:10.1007/3-540-45496-9_2

[28] Shi Y., Sutthiwan P., and Chen L., “Textural Features for Steganalysis,” Information Hiding, 14th International Conference, Berkeley, pp. 63-77, 2013.

[29] Veena T. and Arivazhagan S., “Universal Secret Payload Location Identification in Spatial LSB Stego Images,” Annals of Telecommunications, vol. 74, no. 5, pp. 273-286, 2019.

[30] Veena T. and Arivazhagan S., “Quantitative Steganalysis of Spatial LSB Based Stego Images Using Reduced Instances and Features,” Pattern Recognition Letters, vol. 105, pp. 39-49, 2018.

[31] Veena T. and Selvaraj A., “Local Descriptor Based Steganalysis of Spatial LSB Variant Stego Images,” in Proceedings of the International Conference on Computation, Karaikudi, 2016. 21_Local_descriptor_based_

[32] Wang L., Xu Y., Zhai L., Ren Y., and Du B., “A Posterior Evaluation Algorithm of Steganalysis Accuracy Inspired by Residual Co-Occurrence Probability,” Pattern Recognition, vol. 87, pp. 106- 17, 2019.

[33] Xie G., Ren J., Marshall S., Zhao H., and Li R., “Self-Attention Enhanced Deep Residual Network 242 The International Arab Journal of Information Technology, Vol. 21, No. 2, March 2024 for Spatial Image Steganalysis,” Digital Signal Processing, vol. 139, pp. 104063, 2023.

[34] Yang L., Men M., Xue Y., Wen J., and Zhong P., “Transfer Subspace Learning Based on Structure Preservation for JPEG Image Mismatched Steganalysis,” Signal Processing: Image Communication, vol. 90, pp. 116052, 2021.

[35] Yelchuri R., Dash J., Singh P., Mahapatro A., and Panigrahi S., “Exploiting Deep and Hand-Crafted Features for Texture Image Retrieval Using Class Membership,” Pattern Recognition Letters, vol. 160, pp. 163-71, 2022.

[36] Zavalsız M., Alhajj S., Sailunaz K., Ozyer T., and Alhajj R., “A Comparative Study of Different Pre- Trained Deep Learning Models and Custom CNN for Pancreatic Tumor Detection,” The International Arab Journal of Information Technology, vol. 20, no. 3A, 2023.