Pendekatan Pembelajaran Mesin Berbasis Model Campuran Gaussian untuk Deteksi Steganografi Pada Citra JPEG

  • Indrawan Ady Saputro STMIK AMIKOM Surakarta
  • Febrianta Surya Nugraha STMIK AMIKOM Surakarta
  • Lilik Sugiarto STMIK AMIKOM Surakarta
PDF
DOI https://doi.org/10.31544/jtera.v9.i2.2024.63-68
Published 2025-03-29
Full Text Preview
Download PDF

Abstract

Perkembangan keamanan digital terus mengalami kemajuan pesat, khususnya di bidang steganografi. Steganografi adalah teknik menyembunyikan data agar tidak mudah terdeteksi. Salah satu teknik populer pada citra JPEG adalah Least Significant Bit (LSB). Namun, teknik ini sering disalahgunakan, sehingga meningkatkan risiko terhadap keamanan data dan menuntut adanya metode deteksi yang andal. Tujuan penelitian ini adalah mengembangkan metode deteksi steganografi yang efektif dengan menggunakan Gaussian Mixture Models (GMM). Metodologi yang digunakan melibatkan pengolahan dataset yang terdiri dari dua kelas: citra asli dan citra yang telah disisipkan pesan tersembunyi menggunakan teknik LSB. Dataset ini kemudian dianalisis menggunakan model GMM untuk mendeteksi pola-pola steganografi. Hasil evaluasi menunjukkan bahwa GMM mencapai akurasi 78,67%, presisi 89,15%, dan recall 69,70%. Selain itu, nilai AUC-ROC sebesar 86,59% menunjukkan kemampuan yang baik dalam membedakan citra asli dan steganografi. Kesimpulannya, GMM merupakan metode yang efektif dan efisien untuk deteksi steganografi adaptif, menawarkan tingkat akurasi tinggi dengan kebutuhan sumber daya yang lebih ringan dibandingkan metode lain.

Keywords

Deteksi GMM Keamanan Digital LSB Steganografi

References

H. Zhang, J. Liu, and W. Zhang, “Steganography detection in digital images: A comprehensive review,” J. Inf. Secur. Appl., vol. 58, p. 102520, 2021, doi: 10.1016/j.jisa.2021.102520.
A. Purbaningrum, K. S. Amalia, and I. A. Saputro, “Penerapan Metode Least Significant Bit ( LSB ) dalam Menyisipkan Pesan Rahasia pada Citra Digital : Sebuah Pendekatan Steganografi,” in Prosiding SEMINAR NASIONAL AMIKOM SURAKARTA (SEMNASA) 2023, 2023, no. November, pp. 176–183.
K. Wang and J. Wu, “Analysis and Improvement of LSB Steganography Detection Techniques,” Digit. Signal Process., vol. 116, p. 103055, 2021.
W. Wu, X. Yang, and G. Li, “Robust image steganography detection using deep learning techniques,” Neurocomputing, vol. 430, pp. 32–44, 2021, doi: 10.1016/j.neucom.2021.02.052.
K. Karampidis, E. Kavallieratou, and G. Papadourakis, “A review of image steganalysis techniques for digital forensics,” J. Inf. Secur. Appl., vol. 40, pp. 217–235, 2018, doi: https://doi.org/10.1016/j.jisa.2018.04.005.
Y. Xu, J. Zhang, and Y. Zhao, “Image steganography detection using Gaussian mixture model and machine learning,” J. Electr. Eng. & Technol., vol. 18, no. 2, pp. 623–630, 2023, doi: 10.1007/s42835-023-01779-3.
I. McAteer, A. Ibrahim, G. Zheng, W. Yang, and C. Valli, “Integration of Biometrics and Steganography: A Comprehensive Review,” Technologies, vol. 7, no. 2, 2019, doi: 10.3390/technologies7020034.
A. P. Ratnasari and F. A. Dwiyanto, “Metode Steganografi Citra Digital,” Sains, Apl. Komputasi dan Teknol. Inf., vol. 2, no. 2, p. 52, 2020, doi: 10.30872/jsakti.v2i2.3300.
B. Li and J. Zhang, “Detection of adaptive steganography using statistical features and machine learning algorithms,” Comput. Mater. & Contin., vol. 70, no. 2, pp. 2855–2870, 2022, doi: 10.32604/cmc.2022.022702.
C. M. Azzura, M. Pratiwi, and D. Desyanti, “Implementasi Watermarking Desain Citra Menggunakan Metode Modifikasi End of File (Meof),” JUTEKINF (Jurnal Teknol. Komput. dan Informasi), vol. 11, no. 1, pp. 1–9, 2023, doi: 10.52072/jutekinf.v11i1.473.
C.Nagesh, N. K. Kumar, G. S. Gowd, and G. P. Reddy, “Adaptive Artificial Intelligence Techniques for QoS and Congestion Management in 5G Wireless Networks: A Literature,” INTERANTIONAL J. Sci. Res. Eng. Manag., vol. null, p. null, 2024, doi: 10.55041/ijsrem36077.
M. Ahmed and S. Ramani, “Deep convolutional networks for steganography detection: A comparative analysis,” Comput. & Secur., vol. 107, p. 102278, 2022, doi: 10.1016/j.cose.2021.102278.
X. Zhang, R. Liu, and Y. Zhao, “Integrating Cipher Keys with GMM for Steganography Detection,” J. Inf. Secur. Appl., vol. 74, p. 103491, 2024.
K. Patel and S. Das, “A novel approach for steganography detection using Gaussian mixture model and ensemble classifiers,” J. Appl. Comput. Sci. & Math., vol. 22, no. 1, pp. 13–26, 2024, doi: 10.1007/s41451-024-00539-7.
A. Widyanto, K. Kusrini, and K. Kusnawi, “Pengaruh Keseimbangan Data terhadap Akurasi Model Support Vector Machine pada Data Set Donor Darah,” J. Teknol. Terpadu, vol. 9, no. 2, pp. 79–88, 2023, doi: 10.54914/jtt.v9i2.771.
Y. Yohannes, M. E. Al Rivan, S. Devella, and M. Meiriyama, “Klasifikasi Motif Songket Palembang menggunakan Support Vector Machine berdasarkan Histogram of Oriented Gradients,” J. Teknol. Terpadu, vol. 9, no. 2, pp. 143–149, 2023, doi: 10.54914/jtt.v9i2.1032.
P. Suresh and D. Kumar, “A novel machine learning-based approach for detecting adaptive steganography in digital images,” J. Digit. Forensics, Secur. Law, vol. 18, no. 1, pp. 54–69, 2023, doi: 10.15394/jdfsl.2023.2116.
M. Rijal, A. M. Yani, and A. Rahman, “Deteksi Citra Daun untuk Klasifikasi Penyakit Padi menggunakan Pendekatan Deep Learning dengan Model CNN,” J. Teknol. Terpadu, vol. 10, no. 1, pp. 56–62, 2024, doi: 10.54914/jtt.v10i1.1224.
H. Haeruddin, H. Herman, and P. P. Hendri, “Pengembangan Aplikasi Emoticon Recognition dan Facial Recognition menggunakan Algoritma Local Binary Pattern Histogram (LBPH) dan Convolutional Neural Network (CNN),” J. Teknol. Terpadu, vol. 9, no. 1, pp. 49–55, 2023, doi: 10.54914/jtt.v9i1.613.

Issue

Vol. 9 No. 2: December 2024

Section

Articles

License

Authors who publish with this journal agree to the following terms:

The copyright to this article is transferred to JTERA if and when the article is accepted for publication. The undersigned hereby transfers any and all rights in and to the paper including without limitation all copyrights to JTERA. The undersigned hereby represents and warrants that the paper is original and that he/she is the author of the paper, except for material that is clearly identified as to its original source, with permission notices from the copyright owners where required. The undersigned represents that he/she has the power and authority to make and execute this assignment. The copyright transfer form will be sent via email before the article published.

The corresponding author signs for and accepts responsibility for releasing this material on behalf of any and all co-authors. This agreement is to be signed by at least one of the authors who have obtained the assent of the co-author(s) where applicable. After submission of this agreement signed by the corresponding author, changes of authorship or in the order of the authors listed will not be accepted.

How to Cite

[1]
“Pendekatan Pembelajaran Mesin Berbasis Model Campuran Gaussian untuk Deteksi Steganografi Pada Citra JPEG”, JTERA, vol. 9, no. 2, pp. 63–68, Mar. 2025, doi: 10.31544/jtera.v9.i2.2024.63-68.