Lightweight Models for Real-Time Steganalysis: A Comparison of MobileNet, ShuffleNet, and EfficientNet
Abstract
In the digital age, the security of communication technologies is paramount, with cybercrime projected to reach $10.5 trillion annually by 2025. While encryption is vital, decrypted data remains vulnerable, prompting the exploration of steganography as an additional security layer. Steganography conceals data within digital media, but its misuse for cyberattacks—such as embedding malware—has highlighted the need for steganalysis, the detection of hidden data. Despite extensive research, few studies have explored lightweight deep learning models for real-time steganalysis in resource-constrained environments like mobile devices. This research evaluates MobileNet, ShuffleNet, and EfficientNet for such tasks, using the BOSSbase-1.01 dataset. Models were assessed based on accuracy, computational efficiency, and resource usage. MobileNet achieved the highest computational speed but with only 63.8% accuracy, falling short of practical application. ShuffleNet and EfficientNet performed at random-guessing levels with 50% accuracy, reflecting the challenges of steganalysis on mobile platforms. Future work aims to improve accuracy by integrating advanced preprocessing techniques, attention mechanisms, and hybrid architectures, as well as leveraging ensemble methods for improved detection. Data augmentation, transfer learning, and hyperparameter tuning will also be explored to optimize model performance. This study contributes by identifying these challenges and offering insights for future research, focusing on optimizing models and preprocessing techniques to enhance detection accuracy in resource-constrained environments.
Downloads
References
S. Kemp, “Digital 2023: Global Overview Report,” DataReportal – Global Digital Insights. Accessed: Sep. 28, 2024. [Online]. Available: https://datareportal.com/reports/digital-2023-global-overview-report
entrust, “2022 Global Encryption Trends Study | Entrust.” Accessed: Sep. 28, 2024. [Online]. Available: https://www.entrust.com/resources/reports/global-encryption-trends-study
P. Ponemon, “2024 State of Zero Trust & Encryption Study,” 2024.
G. Li, S. Li, M. Li, X. Zhang, and Z. Qian, “Steganography of Steganographic Networks,” arXiv.org. Accessed: Sep. 28, 2024. [Online]. Available: https://arxiv.org/abs/2302.14521v1
McAfee, “2021 Threat Predictions Report,” McAfee Blog. Accessed: Sep. 28, 2024. [Online]. Available: https://www.mcafee.com/blogs/other-blogs/mcafee-labs/2021-threat-predictions-report/
S. Kaur, S. Singh, M. Kaur, and H.-N. Lee, “A Systematic Review of Computational Image Steganography Approaches,” Arch Computat Methods Eng, vol. 29, no. 7, pp. 4775–4797, Nov. 2022, doi: 10.1007/s11831-022-09749-0.
M. Broz, “How many photos are there? (Statistics & trends in 2024).” Accessed: Oct. 14, 2024. [Online]. Available: https://photutorial.com/photos-statistics/
S. Agarwal, H. Kim, and K.-H. Jung, “High-Pass-Kernel-Driven Content-Adaptive Image Steganalysis Using Deep Learning,” Mathematics, vol. 11, no. 20, Art. no. 20, Jan. 2023, doi: 10.3390/math11204322.
L. I. Hao, Z. Yi, W. Jinwei, Z. Weiming, and L. U. O. Xiangyang, “Lightweight Steganography Detection Method Based on Multiple Residual Structures and Transformer,” dzxbyw, vol. 33, no. 4, pp. 965–978, Jul. 2024, doi: 10.23919/cje.2022.00.452.
L. Liu, L. Meng, X. Wang, and Y. Peng, “An image steganography scheme based on ResNet,” Multimed Tools Appl, vol. 81, no. 27, pp. 39803–39820, Nov. 2022, doi: 10.1007/s11042-022-13206-2.
Y. Zhang, “Image steganalysis method based on integrated GoogleNet,” in 2022 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS), Dalian, China: IEEE, Dec. 2022, pp. 1–4. doi: 10.1109/TOCS56154.2022.10015953.
Y. Yousfi, J. Butora, E. Khvedchenya, and J. Fridrich, “ImageNet Pre-trained CNNs for JPEG Steganalysis,” in 2020 IEEE International Workshop on Information Forensics and Security (WIFS), Dec. 2020, pp. 1–6. doi: 10.1109/WIFS49906.2020.9360897.
W. Mazurczyk and L. Caviglione, “Steganography in Modern Smartphones and Mitigation Techniques,” Aug. 27, 2014, arXiv: arXiv:1410.6796. Accessed: Nov. 08, 2024. [Online]. Available: http://arxiv.org/abs/1410.6796
N. Chen and B. Chen, “Defending against OS-Level Malware in Mobile Devices via Real-Time Malware Detection and Storage Restoration,” Journal of Cybersecurity and Privacy, vol. 2, no. 2, Art. no. 2, Jun. 2022, doi: 10.3390/jcp2020017.
A. G. Howard et al., “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” Apr. 16, 2017, arXiv: arXiv:1704.04861. Accessed: Dec. 18, 2023. [Online]. Available: http://arxiv.org/abs/1704.04861
X. Zhang, X. Zhou, M. Lin, and J. Sun, “ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices,” Dec. 07, 2017, arXiv: arXiv:1707.01083. Accessed: Mar. 20, 2024. [Online]. Available: http://arxiv.org/abs/1707.01083
M. Tan and Q. V. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” Sep. 11, 2020, arXiv: arXiv:1905.11946. doi: 10.48550/arXiv.1905.11946.
T. Paul, S. Ghosh, and A. Majumder, “A Study and Review on Image Steganography,” in Computer Networks and Inventive Communication Technologies, S. Smys, R. Bestak, R. Palanisamy, and I. Kotuliak, Eds., Singapore: Springer Nature, 2022, pp. 523–531. doi: 10.1007/978-981-16-3728-5_40.
M. A. Aslam et al., “Image Steganography using Least Significant Bit (LSB) - A Systematic Literature Review,” in 2022 2nd International Conference on Computing and Information Technology (ICCIT), Jan. 2022, pp. 32–38. doi: 10.1109/ICCIT52419.2022.9711628.
D. Nashat and L. Mamdouh, “An efficient steganographic technique for hiding data,” Journal of the Egyptian Mathematical Society, vol. 27, no. 1, p. 57, Dec. 2019, doi: 10.1186/s42787-019-0061-6.
R. Chandramouli, M. Kharrazi, and N. Memon, “Image Steganography and Steganalysis: Concepts and Practice,” 2004.
R. A, R. Agustina, and Hidayatulloh, “Comparison of Discrete Cosine Transforms (DCT), Discrete Fourier Transforms (DFT), and Discrete Wavelet Transforms (DWT) in Digital Image Watermarking,” ijacsa, vol. 8, no. 2, 2017, doi: 10.14569/IJACSA.2017.080232.
K. Choudhary, “Image Steganography and Global Terrorism,” IOSRJCE, vol. 1, no. 2, pp. 34–48, 2012, doi: 10.9790/0661-0123448.
H. Kheddar, M. Hemis, Y. Himeur, D. Megías, and A. Amira, “Deep Learning for Steganalysis of Diverse Data Types: A review of methods, taxonomy, challenges and future directions,” Neurocomputing, vol. 581, p. 127528, May 2024, doi: 10.1016/j.neucom.2024.127528.
A. K. Sahu and M. Sahu, “Digital image steganography and steganalysis: A journey of the past three decades,” Open Computer Science, vol. 10, no. 1, pp. 296–342, Jan. 2020, doi: 10.1515/comp-2020-0136.
J. Fridrich and M. Goljan, “On estimation of secret message length in LSB steganography in spatial domain,” presented at the Electronic Imaging 2004, E. J. Delp Iii and P. W. Wong, Eds., San Jose, CA, Jun. 2004, p. 23. doi: 10.1117/12.521350.
T. Pevný, P. Bas, and J. Fridrich, “Steganalysis by Subtractive Pixel Adjacency Matrix,” 2009.
A. D. Ker and T. Pevný, “A new paradigm for steganalysis via clustering,” presented at the IS&T/SPIE Electronic Imaging, N. D. Memon, J. Dittmann, A. M. Alattar, and E. J. Delp Iii, Eds., San Francisco Airport, California, USA, Feb. 2011, p. 78800U. doi: 10.1117/12.872888.
X. Zhao, L. Wang, Y. Zhang, X. Han, M. Deveci, and M. Parmar, “A review of convolutional neural networks in computer vision,” Artif Intell Rev, vol. 57, no. 4, p. 99, Mar. 2024, doi: 10.1007/s10462-024-10721-6.
M. Boroumand, M. Chen, and J. Fridrich, “Deep Residual Network for Steganalysis of Digital Images,” IEEE Trans.Inform.Forensic Secur., vol. 14, no. 5, pp. 1181–1193, May 2019, doi: 10.1109/TIFS.2018.2871749.
Y. Ge, T. Zhang, H. Liang, Q. Jiang, and D. Wang, “A Novel Technique for Image Steganalysis Based on Separable Convolution and Adversarial Mechanism,” Electronics, vol. 10, no. 22, p. 2742, Nov. 2021, doi: 10.3390/electronics10222742.
G. Xu, H.-Z. Wu, and Y.-Q. Shi, “Structural Design of Convolutional Neural Networks for Steganalysis,” IEEE Signal Process. Lett., vol. 23, no. 5, pp. 708–712, May 2016, doi: 10.1109/LSP.2016.2548421.
F. Melo, “Area under the ROC Curve,” in Encyclopedia of Systems Biology, W. Dubitzky, O. Wolkenhauer, K.-H. Cho, and H. Yokota, Eds., New York, NY: Springer, 2013, pp. 38–39. doi: 10.1007/978-1-4419-9863-7_209.
S. Guznov, J. Lyons, A. Nelson, and M. Woolley, “The Effects of Automation Error Types on Operators’ Trust and Reliance,” in Virtual, Augmented and Mixed Reality, S. Lackey and R. Shumaker, Eds., Cham: Springer International Publishing, 2016, pp. 116–124. doi: 10.1007/978-3-319-39907-2_11.
J. R. Lyle, B. Guttman, J. M. Butler, K. Sauerwein, C. Reed, and C. E. Lloyd, “Digital investigation techniques : a NIST scientific foundation review,” National Institute of Standards and Technology (U.S.), Gaithersburg, MD, NIST IR 8354, Nov. 2022. doi: 10.6028/NIST.IR.8354.
W.-B. Lin, T.-H. Lai, and K.-C. Chang, “Statistical feature-based steganalysis for pixel-value differencing steganography,” EURASIP Journal on Advances in Signal Processing, vol. 2021, no. 1, p. 87, Sep. 2021, doi: 10.1186/s13634-021-00797-5.
J. Hu, L. Shen, S. Albanie, G. Sun, and E. Wu, “Squeeze-and-Excitation Networks,” May 16, 2019, arXiv: arXiv:1709.01507. doi: 10.48550/arXiv.1709.01507.
P. Ramachandran, N. Parmar, A. Vaswani, I. Bello, A. Levskaya, and J. Shlens, “Stand-Alone Self-Attention in Vision Models,” Jun. 13, 2019, arXiv: arXiv:1906.05909. doi: 10.48550/arXiv.1906.05909.
A. Khan et al., “A survey of the vision transformers and their CNN-transformer based variants,” Artif Intell Rev, vol. 56, no. 3, pp. 2917–2970, Dec. 2023, doi: 10.1007/s10462-023-10595-0.
Z. Jiao, H. Zhang, and X. Li, “CNN2GNN: How to Bridge CNN with GNN,” Apr. 23, 2024, arXiv: arXiv:2404.14822. doi: 10.48550/arXiv.2404.14822.
F. M. Quiroga, F. Ronchetti, L. Lanzarini, and A. Fernandez-Bariviera, “Revisiting Data Augmentation for Rotational Invariance in Convolutional Neural Networks,” Oct. 12, 2023, arXiv: arXiv:2310.08429. doi: 10.48550/arXiv.2310.08429.
O. Dhifallah and Y. M. Lu, “On the Inherent Regularization Effects of Noise Injection During Training,” Feb. 15, 2021, arXiv: arXiv:2102.07379. doi: 10.48550/arXiv.2102.07379.
T. Kumar, A. Mileo, R. Brennan, and M. Bendechache, “Image Data Augmentation Approaches: A Comprehensive Survey and Future directions,” Mar. 12, 2023, arXiv: arXiv:2301.02830. doi: 10.48550/arXiv.2301.02830.
S. Kornblith, J. Shlens, and Q. V. Le, “Do Better ImageNet Models Transfer Better?,” Jun. 17, 2019, arXiv: arXiv:1805.08974. doi: 10.48550/arXiv.1805.08974.
C. Arnold, L. Biedebach, A. Küpfer, and M. Neunhoeffer, “The role of hyperparameters in machine learning models and how to tune them,” Political Science Research and Methods, vol. 12, no. 4, pp. 841–848, Oct. 2024, doi: 10.1017/psrm.2023.61.
Copyright (c) 2024 Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
This work is licensed under a Creative Commons Attribution 4.0 International 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 ;
