Enhancement of LSB Matching Steganography using Multiobjective Optimization Embedding to Improve Security and Imperceptibility

Sabeti, Vajiheh

doi:10.22042/isecure.2025.477842.1172

Enhancement of LSB Matching Steganography using Multiobjective Optimization Embedding to Improve Security and Imperceptibility

Document Type : Research Article

Author

Vajiheh Sabeti

Department of Computer Engineering, Faculty of Engineering, Alzahra University, Tehran, Iran

https://doi.org/10.22042/isecure.2025.477842.1172

Abstract

Least Significant Bit Matching (LSBM) is a simple steganography approach that has been detected under multiple attacks. Imperceptibility (i.e., maintenance of high perceptual image quality) and security are significant parameters in steganography. However, most conventional steganography techniques rely on single-objective optimization, which focuses on improving one parameter while often compromising others. This limitation underscores the need for approaches that balance conflicting objectives. To address this, the present study employs the Non-Dominated Sorting Genetic Algorithm II (NSGA-II) to optimize security and imperceptibility. This methodology includes a cover image division into blocks, each with two critical decisions: (1) seed determination for the pseudo-random number generator to simultaneously identify optimal pixels for data embedding and (2) selecting whether the pixel value should be increased or reduced upon a mismatch between the data bit and pixel LSB. Pixels with the highest data bit–LSB correspondence are optimal, and a pixel value change (increase or reduction) is to minimize block histogram variation. This multiobjective optimization is carried out using NSGA-II. It was comparatively revealed that the developed methodology remarkably improved image quality metrics and decreased detection accuracy at different embedding rates. At embedding rates of 0.3, 0.5, and 0.8 bpp, the Peak Signal-to-Noise Ratio (PSNR) was approximately 57.65, 55.55, and 52.75, respectively. This result represents a 1.5-2.5% improvement compared to conventional LSBM techniques.

Keywords

Steganography

Steganalysis

Least Significant Bit Matching (LSBM)

Non-Dominated Sorting Genetic Algorithm II (NSGA-II)

[1] O. Torki, M. Ashouri-Talouki, and M. Mahdavi. Hierarchical deterministic wallets for secure steganography in blockchain. ISC Int. J.Inf. Secur., 15(1):73–81, jan 2023.
[2] I. J. Kadhim, P. Premaratne, P. J. Vial, and B. Halloran. Comprehensive survey of image steganography: Techniques, evaluations, and trends in future research. Neurocomputing, 335:299–326, mar 2019.
[3] V. Sabeti and A. Aghabagheri. Developing an adaptive dct-based steganography method using a genetic algorithm. Multimed. Tools Appl.,82(13):19323–19346, may 2023.
[4] B. Song, P. Wei, S. Wu, Y. Lin, and W. Zhou. A survey on deep-learning-based image steganography. Expert Syst. Appl., 254:124390, nov 2024.
[5] P. N. Andono and D. R. I. M. Setiadi. Quantization selection based on characteristic of cover image for pvd steganography to optimize imperceptibility and capacity. Multimed. Tools Appl., 82(3):3561–3580, jan 2023.
[6] P. Maniriho and T. Ahmad. Information hiding scheme for digital images using difference expansion and modulus function. J. King Saud Univ. Comput. Inf. Sci., 31(3):335–347, jul 2019.
[7] N. Cevik, T. Cevik, O. Osman, A. Gurhanli, S. Nematzadeh, and F. Sahin. Improved exploiting modification direction steganography for hexagonal image processing. J. King Saud Univ.Comput. Inf. Sci., 34(10):9273–9283, nov 2022. Part B.
[8] A. Westfeld and A. Pfitzmann. Attacks on steganographic systems. In A. Pfitzmann, editor, Information Hiding, volume 1768 of Lecture Notes in Computer Science, pages 61–76. Springer Berlin Heidelberg, Berlin, Heidelberg, 2000.
[9] J. Fridrich, M. Goljan, and R. Du. Detecting lsb steganography in color, and gray-scale images. IEEE Multimed., 8(4):22–28, oct 2001.
[10] S. Dumitrescu, X. Wu, and Z. Wang. Detection of lsb steganography via sample pair analysis. In F. A. P. Petitcolas, editor, Information Hiding, volume 2578 of Lecture Notes in Computer Science, pages 355–372. Springer Berlin Heidelberg, Berlin, Heidelberg, 2003.
[11] A. D. Ker and R. B¨ohme. Revisiting weighted stego-image steganalysis. In E. J. Delp Iii, P. W.Wong, J. Dittmann, and N. D. Memon, editors, Electronic Imaging 2008, page 681905, San Jose, CA, feb 2008.
[12] S. N. M. Al-Faydi, S. K. Ahmed, and H. N. Y.Al-Talb. Improved lsb image steganography with high imperceptibility based on cover-stego matching. IET Image Process., 17(7):2072–2082, may 2023.
[13] S. Hossain, S. Mukhopadhyay, B. Ray, S. K.Ghosal, and R. Sarkar. A secured image steganography method based on ballot transform and genetic algorithm. Multimed. Tools Appl.,81(27):38429–38458, nov 2022.
[14] S. Rustad, D. R. I. M. Setiadi, A. Syukur, and P. N. Andono. Inverted lsb image steganography using adaptive pattern to improve imperceptibility. J. King Saud Univ. - Comput. Inf. Sci.,34(6):3559–3568, jun 2022. Part B.
[15] G. Cancelli, G. Doerr, M. Barni, and I. J. Cox.A comparative study of ± steganalyzers. In 2008 IEEE 10th Workshop on Multimedia Signal Processing, pages 791–796, oct 2008.
[16] M. Fateh, M. Rezvani, and Y. Irani. A new method of coding for steganography based on lsb matching revisited. Secur. Commun. Netn., 2021(1):6610678, 2021.
[17] V. Sabeti, S. Faiazi, and H. Shirinkhah. Improving security of lsbm steganography using of genetic algorithm, multi-key and blocking. Available: https://www.sid.ir/paper/228423/en,2020.
[18] C. Wang, X. Li, B. Yang, X. Lu, and C. Liu. A content-adaptive approach for reducing embedding impact in steganography. In 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, pages 1762–1765, mar 2010.
[19] K. Loukhaoukha, J. Chouinard, and M. H. Taieb. Optimal image watermarking algorithm based on lwt-svd via multi-
objective ant colony optimization. Available:https://www.semanticscholar.org/paper/Optimal-Image-Watermarking-Algorithm-Based-on-via-Loukhaoukha-Chouinard/ddd620a5b9a78f5926924451a367134208e193f2, 2011. Accessed: Aug. 04, 2024.
[20] K. Loukhaoukha. Image watermarking algorithm based on multiobjective ant colony optimization and singular value decomposition in wavelet domain. J. Optim., 2013:1–10, 2013.
[21] M. Mubeen, S. A. M. Gilani, and K. Zafar. Robust image watermarking in contourlet domain using multi objective genetic algorithm. In Eighth International Conference on Digital Information Management (ICDIM 2013), pages 67–72, sep 2013.
[22] J.-S. Lee, J.-W. Wang, and K.-Y. Giang. A new image watermarking scheme using multiobjective bees algorithm. Appl. Math. Inf. Sci.,8(6):2945–2953, nov 2014.
[23] M. Suresh and I. Shatheesh Sam. Optimized interesting region identification for video steganography using fractional grey wolf optimization along with multi-objective cost function. J. King Saud Univ. - Comput. Inf. Sci., 34(6):3489–3496, jun 2022.
[24] M. H. Noor Azam, F. H. Mohd Ridzuan, and M. N. S. Mohd Sayuti. Optimized cover selection for audio steganography using multi-objective evolutionary algorithm. J. Inf. Commun. Technol., 22, 2023.
[25] Z. Yin, Y. Ji, and B. Luo. Reversible data hiding in jpeg images with multi-objective optimization. IEEE Trans. Circuits Syst. Video Technol.,30(8):2343–2352, aug 2020.
[26] M. Kaur, V. Kumar, and D. Singh. An efficient image steganography method using multiobjective differential evolution. In Digital Media Steganography, pages 65–79. Elsevier, 2020.
[27] N. Subramanian, O. Elharrouss, S. Al-Maadeed, and A. Bouridane. Image steganography: A review of the recent advances. IEEE Access, 9:23409–23423, 2021.
[28] A. G. Devi, A. Thota, G. Nithya, S. Majji, A. Gopatoti, and L. Dhavamani. Advancement of digital image steganography using deep convolutional neural networks. In 2022 International Interdisciplinary Humanitarian Conference for Sustainability (IIHC), pages 250–254, nov 2022.
[29] A. Mart´ın, A. Hern´andez, M. Alazab, J. Jung, and D. Camacho. Evolving generative adversarial networks to improve image steganography. Expert Syst. Appl., 222:119841, jul 2023.
[30] W. Luo, W. Huang, R. Fan, R. Shi, and Y. Q.Shi. A comprehensive survey of digital image steganography and steganalysis. APSIPA Trans. Signal Inf. Process., 13(1), nov 2024.
[31] H.-W. Tseng and H.-S. Leng. A reversible modified least significant bit (lsb) matching revisited method. Signal Process. Image Commun.,101:116556, feb 2022.
[32] C. Kim, L. Cavazos Quero, K.-H. Jung, and L. Leng. Advanced dual reversible data hiding: A focus on modification direction and enhanced least significant bit (lsb) approaches. Appl. Sci., 14(6):2437, mar 2024.
[33] T. D. Nguyen and H. Q. Le. A novel secure image steganography scheme based on hamming encoding and lsb matching revisited using lah transform. Multimed. Tools Appl., feb 2024.
[34] W. Wu and H. Li. A novel scheme for random sequential high-capacity data hiding based on pvd and lsb. Signal Image Video Process., 18(3):2277–2287, apr 2024.
[35] V. Sabeti. Unmistakable information embedding into the integer wavelet transform domain of an image using an xor function and a genetic algorithm. Multimed. Tools Appl., 83(8):23655–23688, aug 2023.
[36] R. Wazirali, W. Alasmary, M. M. E. A. Mahmoud, and A. Alhindi. An optimized steganography hiding capacity and imperceptibly using genetic algorithms. IEEE Access, 7:133496–133508, 2019.
[37] P. D. Shah and R. Bichkar. Genetic algorithm-based imperceptible image steganography technique with histogram distortion minimization. In V. E. Balas, A. E. Hassanien, S. Chakrabarti, and L. Mandal, editors, Lecture Notes on Data
Engineering and Communications Technologies, volume 62, pages 267–278. Springer Singapore, Singapore, 2021.
[38] P. D. Shah and R. S. Bichkar. A secure spatial domain image steganography using genetic algorithm and linear congruential generator. In International Conference on Intelligent Computing and Applications, pages 119–129, 2018.
[39] S. Khan. Ant colony optimization (aco) based data hiding in image complex region. Int. J.Electr. Comput. Eng. IJECE, 8(1):379, feb 2018.
[40] V. Sabeti and S. Faiazi. Secure image steganography with high visual image quality based on lsbm and genetic algorithm. J. Soft Comput. Inf.Technol., 9(4):70–82, 2020.
[41] R.-Z. Wang, C.-F. Lin, and J.-C. Lin. Image hiding by optimal lsb substitution and genetic algorithm. Pattern Recognit., 34(3):671–683, mar 2001.
[42] H. R. Kanan and B. Nazeri. A novel image steganography scheme with high embedding capacity and tunable visual image quality based on a genetic algorithm. Expert Syst. Appl.,41(14):6123–6130, oct 2014.
[43] R. Roy and S. Laha. Optimization of stego image retaining secret information using genetic algorithm with 8-connected psnr. Procedia Comput.Sci., 60:468–477, jan 2015.
[44] A. Khamrui, D. D. Gupta, S. Ghosh, and S. Nandy. A spatial domain image authentication technique using genetic algorithm. In J. K.Mandal, P. Dutta, and S. Mukhopadhyay, editors, Computational Intelligence, Communications, and Business Analytics, pages 577–584. Springer, Singapore, 2017.
[45] S. M. Douiri and S. Elbernoussi. An ant colony optimisation for data hiding in greyscale images.Int. J. Oper. Res., 29(1):101, 2017.
[46] A. Banharnsakun. Artificial bee colony approach for enhancing lsb based image steganography. Multimed. Tools Appl., 77(20):27491–27504, oct 2018.
[47] A. H. Mohsin, A. I. Al-Maqoshi, R. H. Al-Samarraie, L. A. Jawad, A. M. Ibrahim, and M. A. Al-Maamari. New method of image steganography based on particle swarm optimization algorithm in spatial domain for high embedding capacity.
[48] M. Boryczka and G. Kazana. Hiding information in digital images using ant algorithms. Entropy, 25(7):963, jun 2023.
[49] M. M. Fadel, W. Said, E. A. A. Hagras, and R. Arnous. A fast and low distortion image steganography framework based on natureinspired optimizers. IEEE Access, 11:125768–125789, 2023.
[50] M. A. Hameed, O. A. Abdel-Aleem, and M. Hassaballah. A secure data hiding approach based on least-significant-bit and nature-inspired optimization techniques. J. Ambient Intell. Humaniz.Comput., 14(5):4639–4657, may 2023.
[51] V. Sabeti and S. Faiazi. MOLSBM: A multi-objective lsb matching steganography method. In 2024 11th International Symposium on Telecommunications (IST), pages 738–743, oct 2024.
[52] A. D. Ker. Steganalysis of lsb matching in grayscale images. IEEE Signal Process. Lett., 12(6):441–444, 2005.
[53] G. Cancelli, I. J. Cox, and G. Do¨err. Improved lsb matching steganalysis based on the amplitude of local extrema. In IEEE International Conference on Image Processing, 2008.
[54] M. Ferrara, S. Rasouli, M. Khademi, and M. Salimi. A robust optimization model for a decision-making problem: An application for stock market. Oper. Res. Perspect., 4:136–141, 2017.

[55] K. Deb. An investigation of niche and species formation in genetic function optimization. In ICGA’89, pages 42–50, 1989.
[56] R. Huang, C. Lian, Z. Dai, Z. Li, and Z. Ma. A novel hybrid image synthesis-mapping framework for steganography without embedding. IEEE Access, 11:113176–113188, 2023.
[57] Z. Zhou, Q. Wang, X. Du, X. Liang, C. Sun, Y. Huang, M. Yu, C. Liu, and L. Hu. Latent vector optimization-based generative image steganography for consumer electronic applications. IEEE Trans. Consum. Electron., 70(1):4357–4366, feb 2024.
[58] M. Qasaimeh, A. A. Qtaish, and S. Aljawarneh. Robust steganographic approach using generative adversarial network and compressive autoen-coder. Multimed. Tools Appl., nov 2024.
[59] F. Chen, Q. Xing, and F. Liu. Technology of hiding and protecting the secret image based on two-channel deep hiding network. IEEE Access, 8:21966–21979, 2020.
[60] X. Duan, J. Song, R. Yan, H. Wang, and Z. Zhang. High-capacity image steganography based on improved fc-densenet. IEEE Access, 8:170174–170182, 2020.
[61] S. Baluja. Hiding images in plain sight: deep steganography. In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17, pages 2066–2076, Red Hook, NY, USA, dec 2017. Curran Associates Inc.
[62] A. Khalifa and A. Guzman. Imperceptible image steganography using symmetry-adapted deep learning techniques. Symmetry, 14(7):1325, jul 2022.
[63] Q. Li, S. Cao, Y. Zhao, S. Wang, Q. Guo, and Q. Fu. A novel grayscale image steganography scheme based on chaos encryption and generative adversarial networks. IEEE Access, 8:168166–168176, 2020.
[64] L. Liu, L. Meng, Y. Peng, and X. Wang. A data hiding scheme based on u-net and wavelet transform. Knowl.-Based Syst., 223:107022, jul 2021.
[65] Z. Gan and Y. Zhong. A novel grayscale image steganography via generative adversarial network. In Web Information Systems and Applications, pages 405–417. Springer, Cham, 2021.
[66] F. Huang, B. Li, and J. Huang. Attack lsb matching steganography by counting alteration rate of the number of neighbourhood gray levels. In 2007 IEEE International Conference on Image Processing, pages I–401–I–404, sep 2007.
[67] T. Denemark, V. Sedighi, V. Holub, R. Cogranne, and J. Fridrich. Selection-channel-aware rich model for steganalysis of digital images. In 2014 IEEE International Workshop on Information Forensics and Security (WIFS), pages 48–53, dec 2014.