An Ensemble Transfer Learning Model for Detecting Stego Images
Source abstract
Abstract
As internet traffic grows daily, so does the need to protect it. Network security protects data from unauthorized access and ensures their confidentiality and integrity. Steganography is the practice and study of concealing communications by inserting them into seemingly unrelated data streams (cover media). Investigating and adapting machine learning models in digital image steganalysis is becoming more popular. It has been demonstrated that steganography techniques used within such a framework perform more securely than do techniques using hand-crafted pieces. This work was carried out to investigate and examine machine learning methods’ critical contributions and beneficial roles. Machine learning is a field of artificial intelligence (AI) that provides the ability to learn without being explicitly programmed. Steganalysis is considered a classification problem that can be addressed by employing machine learning techniques and recent deep learning tools. The proposed ensemble model had four models (convolution neural networks (CNNs), Inception, AlexNet, and Resnet50), and after evaluating each model, the system voted on the best model for detecting stego images. Since active steganalysis is a classification problem that may be solved using active deep learning tools and modern machine learning methods, this paper’s major goal was to analyze deep learning algorithms’ vital roles and main contributions. The evaluation shows how to successfully detect images that contain a steganography algorithm that hides data in images. Thus, it suggests which algorithms work best, which need improvement, and which are easier to identify.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Steganography and Watermarking Techniques · Digital Media Forensic Detection · Chaos-based Image/Signal Encryption
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Information System Engineering Department, Technical Engineering College, Erbil Polytechnic University, Erbil 44001, Iraq
Department of Information Technology, College of Engineering and Computer Science, Lebanese French University, Erbil 44001, Iraq
References (31)
Show source-provided references
1. Butora, J., Yousfi, Y., and Fridrich, J. (2021, January 21–25). How to pretrain for steganalysis. Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security, Virtual.10.1145/3437880.3460395 ↗
2. Chaumont, M. (2020). Digital Media Steganography, Academic Press.
3. Universal Image Steganography Detection using Multimodal Deep Learning Framework
4. Data Encryption Standard: Past and future10.1109/5.4441 ↗
5. Yegireddi, R., and Kumar, R.K. (2016, January 18–19). A survey on conventional encryption algorithms of Cryptography. Proceedings of the 2016 International Conference on ICT in Business Industry & Government (ICTBIG), Indore, India.10.1109/ICTBIG.2016.7892684 ↗
6. Ozcan, S., and Mustacoglu, A.F. (2018, January 10–13). Transfer learning effects on image steganalysis with pre-trained deep residual neural network model. Proceedings of the 2018 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA.10.1109/BigData.2018.8622437 ↗
7. GBRAS-Net: A convolutional neural network architecture for spatial image steganalysis10.1109/ACCESS.2021.3052494 ↗
8. Digital image steganalysis: A survey on paradigm shift from machine learning to deep learning based techniques10.1049/ipr2.12043 ↗
9. Płachta, M., Krzemień, M., Szczypiorski, K., and Janicki, A. (2022). Detection of Image Steganography Using Deep Learning and Ensemble Classifiers. Electronics, 11.10.3390/electronics11101565 ↗
10. Deep Learning Applied to Steganalysis of Digital Images: A Systematic Review10.1109/ACCESS.2019.2918086 ↗
11. Sensitivity of deep learning applied to spatial image steganalysis10.7717/peerj-cs.616 ↗
12. Spatial Steganalysis Based on Non-Local Block and Multi-Channel Convolutional Networks10.1109/ACCESS.2022.3199351 ↗
13. Multi-Frequency Residual Convolutional Neural Network for Steganalysis of Color Images10.1109/ACCESS.2021.3119664 ↗
14. Corchado, J.M., and Trabelsi, S. (2022). Sustainable Smart Cities and Territories, Springer International Publishing.10.1007/978-3-030-78901-5 ↗
15. Agarwal, S., Kim, C., and Jung, K.-H. (2022). Steganalysis of Context-Aware Image Steganography Techniques Using Convolutional Neural Network. Appl. Sci., 12.10.3390/app122110793 ↗
16. Yedroudj, M., Comby, F., and Chaumont, M. (2018, January 15–20). Yedroudj-Net: An Efficient Cnn for Spatial Steganalysis. Proceedings of the IEEE ICASSP’ 2018, Calgary, AB, Canada.10.1109/ICASSP.2018.8461438 ↗
17. Stančić, A., Vyroubal, V., and Slijepčević, V. (2022). Classification Efficiency of Pre-Trained Deep CNN Models on Camera Trap Images. J. Imaging, 8.10.3390/jimaging8020020 ↗
18. Fridrich, J., Pevný, T., and Kodovský, J. (2007, January 20–21). Statistically undetectable JPEG steganography: Dead ends, challenges, and opportunities. Proceedings of the the 9th ACM Multimedia & SecurityWorkshop, Dallas, TX, USA.10.1145/1288869.1288872 ↗
19. Universal distortion function for steganography in an arbitrary domain10.1186/1687-417X-2014-1 ↗
20. Using Statistical Image Model for JPEG Steganography: Uniform Embedding Revisited10.1109/TIFS.2015.2473815 ↗
21. Edge adaptive image steganography based on lsb matching revisited10.1109/TIFS.2010.2041812 ↗
22. Minimizing additive distortion in steganography using syndrometrellis codes10.1109/TIFS.2011.2134094 ↗
23. Steganalysis of HUGO steganography based on parameter recognition of syndrome-trellis-codes10.1007/s11042-015-2759-2 ↗
24. (2022, January 18). Break Our Steganographic System Base Webpage (BossBase). Available online: http://agents.fel.cvut.cz/boss/.
25. Medical Image Classification Using Different Machine Learning Algorithms
26. Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover source-mismatch10.2352/ISSN.2470-1173.2016.8.MWSF-078 ↗
27. Wind Speed Prediction for Duhok City Applied Recurrent Neural Network
28. Qian, Y., Dong, J., Wang, W., and Tan, T. (2015, January 8–12). Deep learning for steganalysis via convolutional neural networks. Proceedings of the Media Watermarking, Security, and Forensics 2015, San Francisco, CA, USA.10.1117/12.2083479 ↗
29. Alattar, A.M., Memon, N.D., and Heitzenrater, C.D. (2015). International Society for Optics and Photonics, SPIE.
30. Bayesian Network Structure Discovery Using Antlion Optimization Algorithm
31. Mohamed, N., Rabie, T., Kamel, I., and Alnajjar, K. (2021, January 21–24). Detecting Secret Messages in Images Using Neural Networks. Proceedings of the 2021 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS), Toronto, ON, Canada.10.1109/IEMTRONICS52119.2021.9422500 ↗