Evaluating Steganography Detection in JPEG Images Using Gaussian Mixture Model and Cryptographic Keys
DOI:
https://doi.org/10.29207/resti.v9i6.6084Keywords:
detection, gaussian mixture models, JPEG, machine learning, steganographyAbstract
This study introduces a novel approach that integrates Gaussian Mixture Models (GMM) with MD5 hash-based verification to detect hidden messages embedded via Least Significant Bit (LSB) steganography in JPEG images. Unlike previous methods, the proposed dual-layer technique combines probabilistic modeling with data integrity verification. The model was trained and evaluated using a dataset comprising both original and stego-JPEG images. The experimental results achieved an accuracy of 78.67% and a precision of 89.15%, indicating good class separation between stego and non-stego images (AUC-ROC = 0.8659). However, the recall rate of 69.70% suggests that there is room for improvement in detecting all stego instances. Although MD5 is a hash function rather than an encryption algorithm, it effectively aids in identifying data anomalies resulting from message embedding. Overall, this lightweight approach offers a practical solution for steganalysis and can be further enhanced through the integration of hybrid deep learning techniques in future research.
Downloads
References
F. N. Hakim and M. Sholikhan, “Enhancing Data Security through Digital Image Steganography : An Implementation of the Two Least Significant Bits ( 2LSB ) Method,” Int. J. Graph. Des., vol. 02, no. November, pp. 222–235, 2024, doi: https://doi.org/10.51903/ijgd.v2i2.2124.
R. K. Sahu, “An In-Depth Review of Steganography : Methods , Uses , and Progress in Digital Security,” Ianna J. Interdiscipinary Stud., vol. 7, no. 1, pp. 437–453, 2025, doi: https://unijisedu.com/index.php/ijis/article/view/164.
S. Rahman et al., “A Huffman code LSB based image steganography technique using multi-level encryption and achromatic component of an image,” Sci. Rep., vol. 13, no. 1, p. 14183, 2023, doi: 10.1038/s41598-023-41303-1.
Y. Ma, X. Yu, X. Luo, D. Liu, and Y. Zhang, “Adaptive feature selection for image steganalysis based on classification metrics,” Inf. Sci. (Ny)., vol. 644, p. 118973, 2023, doi: https://doi.org/10.1016/j.ins.2023.118973.
X. Duan, Z. Wang, S. Li, and C. Qin, “StegTransX: A lightweight deep steganography method for high-capacity hiding and JPEG compression resistance,” Inf. Sci. (Ny)., vol. 716, p. 122264, 2025, doi: https://doi.org/10.1016/j.ins.2025.122264.
A. Bisht, A. Singla, and K. Joshi, “A Review on Image Steganography Techniques,” Int. Res. J. Adv. Eng. Hub, vol. 2, pp. 1986–1996, 2024, doi: 10.47392/IRJAEH.2024.0271.
F. Baso, “Digital Privacy Protection: Applying Steganography in Text Messages,” J. Embed. Syst. Secur. Intell. Syst., vol. 5, no. 1, pp. 76–80, 2024, doi: 10.59562/jessi.v5i1.2233.
D. M B Meenavathi and B. K J, “Feature Based Face Recognition using Machine Learning Techniques,” Int. J. Recent Technol. Eng., vol. 8, 2022, doi: 10.35940/ijrte.F7497.038620.
S. Kaushik et al., “Robust machine learning based Intrusion detection system using simple statistical techniques in feature selection,” Sci. Rep., vol. 15, no. 1, p. 3970, 2025, doi: 10.1038/s41598-025-88286-9.
C. M. Weber, J.-A. Park, A. A. Valverde, J. Clark, and K. Sharma, “Gaussian mixture model clustering algorithms for the analysis of high-precision mass measurements,” Nucl. Instruments Methods Phys. Res. Sect. A Accel. Spectrometers, Detect. Assoc. Equip., vol. 1027, p. 166299, 2022, doi: 10.1016/j.nima.2021.166299.
A. U. Nasution, E. P. Ambarita, H. E. Fadlia, and V. A. E. P, “Application of the Gaussian Mixture Models ( GMM ) Algorithm to Identify Error Patterns in Compilation,” JOMLAI J. Mach. Learn. andArtificial Intell., vol. 4, no. 2, 2025, doi: 10.55123/jomlai.v4i2.5960.
E. Aribowo, W. S. Amalya, and N. R. D. Puji Astuti, “Application of LSB Steganography for Encrypted Data Using Triple Transposition Vigenere on Digital Images,” JUITA J. Inform., vol. 13, no. 2 SE-Articles, pp. 157–165, Aug. 2025, doi: 10.30595/juita.v13i2.24592.
S. Rahman et al., “A novel and efficient digital image steganography technique using least significant bit substitution,” Sci. Rep., vol. 15, no. 1, p. 107, 2025, doi: 10.1038/s41598-024-83147-3.
Z. Wu, J. Guo, C. Zhang, and C. Li, “Steganography and Steganalysis in Voice over IP: A Review,” Sensors, vol. 21, no. 4, 2021, doi: 10.3390/s21041032.
L. T. Badar, B. Carminati, and E. Ferrari, “A comprehensive survey on stegomalware detection in digital media, research challenges and future directions,” Signal Processing, vol. 231, p. 109888, 2025, doi: https://doi.org/10.1016/j.sigpro.2025.109888.
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.
D. Y. Mikhail, R. S. Hawezi, and S. W. Kareem, “An Ensemble Transfer Learning Model for Detecting Stego Images,” Appl. Sci., vol. 13, no. 12, 2023, doi: 10.3390/app13127021.
E. M. Jamel, “Image Steganography Based on Wavelet Transform and Histogram Modification,” Ibn AL-Haitham J. Pure Appl. Sci., vol. 33, no. 1, pp. 173–186, 2020, doi: 10.30526/33.1.2365.
O. Kuznetsov, E. Frontoni, K. Chernov, K. Kuznetsova, R. Shevchuk, and M. Karpinski, “Enhancing Steganography Detection with AI: Fine-Tuning a Deep Residual Network for Spread Spectrum Image Steganography,” Sensors, vol. 24, no. 23, 2024, doi: 10.3390/s24237815.
H. Li, Y. Zhang, J. Wang, W. Zhang, and X. Luo, “Lightweight Steganography Detection Method Based on Multiple Residual Structures and Transformer,” Chinese J. Electron., vol. 33, no. 4, pp. 965–978, 2024.
S. Ravikumar, K. Vijay, S. Sanjai, L. Ram Prakash, and H. Pravinesh, “AI Veil: Unravelling Secrets with Machine Learning Steganography,” in Information System Design: AI and ML Applications, 2024, pp. 231–242.
Z. I. Nezami, H. Ali, M. Asif, H. Aljuaid, I. Hamid, and Z. Ali, “An efficient and secure technique for image steganography using a hash function,” PeerJ Comput. Sci., vol. 8, p. e1157, Nov. 2022, doi: 10.7717/peerj-cs.1157.
L. Scrucca, “Entropy-Based Anomaly Detection for Gaussian Mixture Modeling,” Algorithms, vol. 16, p. 195, Apr. 2023, doi: 10.3390/a16040195.
X. Liu, S. Zhu, F. Yang, and S. Liang, “Research on unsupervised anomaly data detection method based on improved automatic encoder and Gaussian mixture model,” J. Cloud Comput., vol. 11, no. 1, p. 58, 2022, doi: 10.1186/s13677-022-00328-z.
H. Tuo, B. Zhu, Y. Li, Z. Ma, S. Long, and Y. Bai, “A Gaussian mixture model (GMM)-based method for photon multiple events identification and centroid localization,” Opt. Commun., vol. 596, p. 132398, 2025, doi: https://doi.org/10.1016/j.optcom.2025.132398.
Y. Tian, L. Zhao, and H. Li, “A machine vision approach for classification and dimensional design of furniture panels using GMM-SVM,” Syst. Soft Comput., vol. 7, p. 200358, 2025, doi: https://doi.org/10.1016/j.sasc.2025.200358.
S. Ghojaria, “Sneakers Image Dataset Pinterest.” 2022. [Online]. Available: https://www.kaggle.com/datasets/saadghojaria/sneakers-image-dataset-pinterest
M. Płachta, M. Krzemień, K. Szczypiorski, and A. Janicki, “Detection of Image Steganography Using Deep Learning and Ensemble Classifiers,” Electronics, vol. 11, p. 1565, 2022, doi: 10.3390/electronics11101565.
X. Gao, J. Yi, L. Liu, and L. Tan, “A Generic Image Steganography Recognition Scheme with Big Data Matching and an Improved ResNet50 Deep Learning Network,” Electronics, vol. 14, no. 8, 2025, doi: 10.3390/electronics14081610.
F. Zhang, Y. Dong, and H. Sun, “Research on Key Technologies of Image Steganography Based on Simultaneous Deception of Vision and Deep Learning Models,” Appl. Sci., vol. 14, no. 22, 2024, doi: 10.3390/app142210458.
A. Akram et al., “Enhanced Steganalysis for Color Images Using Curvelet Features and Support Vector Machine,” Comput. Mater. Contin., vol. 78, no. 1, pp. 1311–1328, 2024, doi: https://doi.org/10.32604/cmc.2023.040512.
N. J. D. La Croix, T. Ahmad, and F. Han, “Comprehensive survey on image steganalysis using deep learning,” Array, vol. 22, p. 100353, 2024, doi: https://doi.org/10.1016/j.array.2024.100353.
N. Farooq and A. Selwal, “Image steganalysis using deep learning: a systematic review and open research challenges,” J. Ambient Intell. Humaniz. Comput., vol. 14, no. 6, pp. 7761–7793, 2023, doi: 10.1007/s12652-023-04591-z.
Downloads
Published
Issue
Section
License
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;
