Peningkatan Keamanan Steganografi Citra Berbasis Least Significant Bit dengan Integrasi Algoritma Deep Learning Convolutional Neural Network (CNN)
DOI:
https://doi.org/10.48144/suryainformatika.v15i1.2080Keywords:
CNN, Deep Learning, Steganografi, Keamanan Data, Least Significant Bit (LSB)Abstract
Steganografi citra merupakan teknik penyembunyian informasi rahasia di dalam gambar digital yang berperan penting dalam komunikasi rahasia. Metode Least Significant Bit (LSB) dikenal luas karena kesederhanaan dan kemudahan implementasinya, namun memiliki kelemahan signifikan dalam hal keamanan, khususnya rentan terhadap deteksi melalui analisis statistik. Penelitian ini bertujuan untuk meningkatkan keamanan steganografi LSB melalui integrasi dengan algoritma deep learning Convolutional Neural Network (CNN). Dataset CIFAR-10 digunakan sebagai media eksperimen dengan proses penyisipan data pada bit paling tidak signifikan dari kanal warna citra digital. Evaluasi dilakukan melalui metrik imperseptibilitas seperti Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), serta akurasi deteksi oleh model steganalisis. Hasil eksperimen menunjukkan bahwa integrasi LSB dengan CNN menghasilkan peningkatan nilai PSNR dan SSIM, serta menurunkan tingkat keberhasilan deteksi pesan tersembunyi oleh pihak ketiga. Pendekatan ini berhasil membuat proses penyisipan data lebih adaptif dan sulit dikenali secara visual maupun statistik, sehingga meningkatkan tingkat keamanan dan kerahasiaan dalam komunikasi digital berbasis steganografi.
References
W. Wei, A. Chengfeng, L. Wang, and H. Ma, A texture synthesis steganography scheme based on super-pixel structure and SVM, vol. 538. Springer International Publishing, 2018. doi: 10.1007/978-3-030-00828-4_38.
M. Khozin and M. A. Soeleman, “Improvement Of Watermarking Quality Using The Least Significant Bit Method With Reed Solomon Code,” vol. 26, no. 1, pp. 50–61, 2024, doi: 10.9790/0661-2601035061.
B. R. Ghosh, S. Banerjee, and J. K. Mandal, “A Survey on LSB Replacement-Based Statistical Image Steganalysis Techniques BT - Advances in Data Science and Computing Technologies,” 2023, pp. 313–320.
R. Roy, A. Sarkar, and S. Changder, “Chaos based Edge Adaptive Image Steganography,” Procedia Technol., vol. 10, pp. 138–146, 2013, doi: 10.1016/j.protcy.2013.12.346.
M. Alia and K. Suwais, “Improved steganography scheme based on fractal set,” Int. Arab J. Inf. Technol., vol. 17, no. 1, pp. 128–136, 2020, doi: 10.34028/iajit/17/1/15.
T. Indriyani, S. Nurmuslimah, A. Taufiqurrahman, R. K. Hapsari, C. N. Prabiantissa, and A. Rachmad, “Steganography on Color Images Using Least Significant Bit (LSB) Method BT - Proceedings of the 1st International Conference on Neural Networks and Machine Learning 2022 (ICONNSMAL 2022),” 2023, pp. 39–48. doi: 10.2991/978-94-6463-174-6_5.
X. Duan, N. Liu, M. Gou, W. Wang, and C. Qin, “SteganoCNN: Image steganography with generalization ability based on convolutional neural network,” Entropy, vol. 22, no. 10, pp. 1–15, 2020, doi: 10.3390/e22101140.
N. Hidayasari, I. Riadi, and Y. Prayudi, “Steganalisis Blind dengan Metode Convolutional Neural Network (CNN) Yedroudj- Net terhadap Tools Steganografi,” J. Teknol. Inf. dan Ilmu Komput., vol. 7, no. 4, pp. 787–796, 2020, doi: 10.25126/jtiik.2020703326.
X. Pan, W. Lin, L. Yang, and Y. Mo, “CNN-based state prediction for a varying number of storage in economic dispatch,” Int. J. Electr. Power Energy Syst., vol. 168, no. January, p. 110590, 2025, doi: 10.1016/j.ijepes.2025.110590.
G. Kaur et al., “Face mask recognition system using CNN model,” Neurosci. Informatics, vol. 2, no. 3, p. 100035, 2022, doi: 10.1016/j.neuri.2021.100035.
Arun, “A CNN based hybrid approach towards automatic image registration,” Geod. Cartogr., vol. 39, Sep. 2013, doi: 10.3846/20296991.2013.840409.
Matlab, “Matlab.” https://www.mathworks.com/discovery/convolutionalneural-network-matlab.html. (accessed Jan. 29, 2022).
C. Neuroscience, “Retracted: Comparative Analysis of Deepfake Image Detection Method Using Convolutional Neural Network,” Comput. Intell. Neurosci., vol. 2023, p. 1, Nov. 2023, doi: 10.1155/2023/9767530.
I. Fathurrahman, Mahpuz, M. Djamaluddin, L. Wijaya, and I. Wahidah, “Pengembangan Model Convolutional Neural Network (CNN) untuk Klasifikasi Penyakit Kulit Berbasis Citra Digital,” Infotek J. Inform. dan Teknol., vol. 8, pp. 298–308, Jan. 2025, doi: 10.29408/jit.v8i1.28655.
