International Journal of Electronics and Computer Applications

Volume: 1 Issue: 2

  • Open Access
  • Review Article

Feature Extraction Approaches for Image Steganalysis: A Review

Jayashri Jagannath Patil1∗, Nilesh Ashok Suryawanshi2

1 Research Scholar, NES’s Gangamai College of Engineering, Nagaon, Dhule, 424005, Maharashtra, India
2 Assistant Professor, NES’s Gangamai College of Engineering, Nagaon, Dhule, 424005, Maharashtra, India

*Corresponding author email: [email protected]
 

Year: 2024, Page: 55-59, Doi: https://doi.org/10.54839/ijeaca.v1i2.2

Received: Sept. 16, 2024 Accepted: Nov. 22, 2024 Published: Dec. 11, 2024

Abstract

Digital image steganography, the concealing of information within seemingly innocent photographs presents considerable hurdles for traditional detection methods. To address this, we provide a unique deep learning-based steganalysis model is designed to identify the hidden data in digital photos. The methods used to detect steganographic content accurately against a variety of steganographic strategies using convolutional neural networks (CNNs) and generative adversarial networks (GANs). Our model has a multi-stage architecture that includes modules for feature extraction, representation learning, and decision-making, all of which are meant to capture complicated patterns indicating steganographic modifications. We use cutting-edge CNN architectures like ResNet and DenseNet for feature extraction, allowing the model to detect tiny visual cues typical of steganographic embedding. Furthermore, to improve the model's capacity to generalize across diverse steganographic procedures and payloads, we incorporate GAN-based data augmentation approaches, allowing it to learn a more thorough representation of steganographic content variants. Experimental results show that our methodology is effective at recognizing steganographic content with high precision and recall rates, beating existing methods across a variety of parameters. Furthermore, we undertake extensive experiments to evaluate the model's resilience to adversarial attacks and capacity to extend to previously unknown steganographic techniques, confirming its robustness and practical usefulness in real-world contexts.

Keywords: Feature Extraction Approaches for Image Steganalysis: A Review

References

  1. Liu S, Zhang C, Wang L, Yang P, Hua S, Zhang T. Image Steganalysis of Low Embedding Rate Based on the Attention Mechanism and Transfer LearningElectronics . 2023;12(4):1–12. Available from: https://doi.org/10.3390/electronics12040969

  2. Shehab DA, Alhaddad MJ. Comprehensive Survey of Multimedia Steganalysis: Techniques, Evaluations, and Trends in Future ResearchSymmetry . 2022;14(1):1–26. Available from: https://doi.org/10.3390/sym14010117

  3. Eid WM, Alotaibi SS, Alqahtani HM, Saleh SQ. Digital Image Steganalysis: Current Methodologies and Future ChallengesIEEE Access. 2022;10:92321 –92336. Available from: https://doi.org/10.1109/ACCESS.2022.3202905

  4. Agarwal S, Kim C, Jung KH. Steganalysis of Context-Aware Image Steganography Techniques Using Convolutional Neural NetworkApplied Science. 2022;12:1–15. Available from: https://doi.org/10.3390/app122110793

  5. Lee H, Lee HW. New Approach on Steganalysis: Reverse-Engineering based Steganography SW Analysis. In: ICSCA '20: Proceedings of the 2020 9th International Conference on Software and Computer Applications. (pp. 212-216) 2020.

  6. Sahu AK, Sahu M. Digital image steganography and steganalysis: A journey of the past three decadesOpen Computer Science. 2020;10:296–342. Available from: https://doi.org/10.1515/comp-2020-0136

  7. Selvaraj A, Ezhilarasan A, Wellington SLJ, Sam AR. Digital image steganalysis: A survey on paradigm shift from machine learning to deep learning based techniquesIET Image Process. 2021;15(2):504–522. Available from: https://doi.org/10.1049/ipr2.12043

  8. Kim J, Park H, JIP. CNN-based image steganalysis using additional data embeddingMultimedia Tools and Applications. 2019;79:1355–1372. Available from: https://doi.org/10.1007/s11042-019-08251-3

  9. Li Q, Feng G, Ren Y, Zhang X. Embedding Probability Guided Network for Image SteganalysisIEEE Signal Processing Letters. 2021;28:1095 –1099. Available from: https://doi.org/10.1109/LSP.2021.3083546

  10. Reinel TS, Brayan AAH, Colombia BOMADoEaIAUAdMM, Alejandro MR, Daniel AG, Alejandro AGJ. GBRAS-Net: A Convolutional Neural Network Architecture for Spatial Image SteganalysisIEEE Access. 2021;9:14340 –14350. Available from: https://doi.org/10.1109/ACCESS.2021.3052494

  11. Liu J, Ke Y, Zhang Z, Lei Y, Li J, Zhang M. Recent Advances of Image Steganography With Generative Adversarial NetworksIEEE Access. 2020;8:60575–60597. Available from: https://doi.org/10.1109/ACCESS.2020.2983175

  12. Subramanian N, Elharrouss O, Al-Maadeed S, Bouridane A. Image Steganography: A Review of the Recent AdvancesIEEE Access . 2021;9:23409 –23423. Available from: https://doi.org/10.1109/ACCESS.2021.3053998

  13. Duan X, Zhang C, Ma Y, Liu S. Preprocessing Enhancement Method for Spatial Domain SteganalysisMathematics. 2022;10(21):1–12. Available from: https://doi.org/10.3390/math10213936

  14. Chanu YJ, Singh M, Tuithung T. Image Steganography and Steganalysis: A SurveyInternational Journal of Computer Applications . 2012;52(2):1–11. Available from: https://research.ijcaonline.org/volume52/number2/pxc3881484.pdf

  15. Liu B, Lin X, Wu Y, Tang Z. Steganalysis based on generative adversarial networks and multi-level feature fusionIEEE Transactions on Information Forensics and Security. 2020;15:1608–1620.

  16. Tang YH, Jiang LH, He HQ, Dong WY. A review on deep learning based image steganalysis. In: 2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC). IEEE. 2018.

  17. Wang H, Pan X, Fan L, Zhao S. Steganalysis of convolutional neural network based on neural architecture searchMultimedia Systems 27(5). 2021;27(5):379–387. Available from: https://link.springer.com/article/10.1007/s00530-021-00779-5

  18. Li X, Li W, Huang Y, Wu QJ. A novel steganalysis method based on deep learning and kernel feature representationIEEE Access. 2020;8:16127–16137.

  19. Luo Y, Huang J. Steganalysis based on generative adversarial networks and ensemble learningIEEE Transactions on Information Forensics and Security. 2020;15:3415–3427.

  20. Liu T, Lin L, Luo H, Li H, Huang J. Steganalysis based on convolutional neural network and transfer learningIEEE Access. 2020;8:12105–12113.

  21. Zhou X, Zhang J, Huang L, Zhu Z. A novel steganalysis method based on hybrid convolutional neural network and attention mechanismIEEE Access. 2020;8:158838–158849.

  22. Fridrich J, Kodovsky J. Rich models for steganalysis of digital imagesIEEE Transactions on Information Forensics and Security. 2012;7(3):868 –882. Available from: https://doi.org/10.1109/TIFS.2012.2190402

  23. Zhang L, Shi YQ, Zhang W, Huang J. Enhanced steganalysis with deep feature fusion and ensemble learningIEEE Transactions on Information Forensics and Security. 2021;16:1208–1223.

  24. Shi YQ, Chen C. Adversarial steganalysis in spatial domainIEEE Transactions on Information Forensics and Security. 2020;15:3433–3448.

  25. Zhang T, Shi YQ. Real-time steganalysis of adaptive steganographyInformation Sciences. 2020;508:499–513.

Cite this article

Patil JJ, Suryawanshi NA. (2024). Feature Extraction Approaches for Image Steganalysis: A Review. International Journal of Electronics and Computer Applications. 1(2): 55-59. https://doi.org/10.54839/ijeaca.v1i2.2


 

Views
58
Downloads
41
Citations