AI-Based and Compressed-Domain Video Steganography: A Systematic Review and Comparative Analysis (2017–2025)

Artificial intelligence has significantly transformed video steganography by improving the security, robustness, and adaptability of secret data embedding techniques. This paper presents a systematic review and comparative analysis of AI-based and compressed-domain video steganography techniques published between 2017 and 2025. Relevant studies were collected from major scientific databases and critically analyzed based on embedding domain, deep learning architecture, dataset, payload capacity, peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), mean square error (MSE), computational complexity, robustness, and resistance to steganalysis attacks. The review highlights the advantages and limitations of convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), transformer-based, and compressed-domain approaches. Comparative analysis indicates that AI-driven techniques generally achieve superior imperceptibility and security compared to conventional methods, although higher computational requirements remain a significant challenge. The study further identifies existing research gaps, discusses practical implementation challenges, and outlines future research directions including lightweight deep learning models, explainable AI, federated learning, and real-time secure multimedia communication systems.

Deep Learning Steganography, GAN, CNN, Video Steganography, Compressed Domain Embedding, Diffusion Models, Multimedia Security

1. Baluja, S. (2017). Hiding images in plain sight: Deep steganography. In Advances in Neural Information Processing Systems, 30, 2069–2079. [Google Scholar] [Crossref]

2. https://scholar.google.com/scholar?q=Hiding+Images+in+Plain+Sight+Deep+Steganography [Google Scholar] [Crossref]

3. Hayes, J., & Danezis, G. (2017). Generating steganographic images via adversarial training. In Advances in Neural Information Processing Systems, 30, 1954–1963. [Google Scholar] [Crossref]

4. https://scholar.google.com/scholar?q=Generating+Steganographic+Images+via+Adversarial+Training [Google Scholar] [Crossref]

5. Volkhonskiy, D., Nazarov, I., Burnaev, E., & Borisenko, A. (2017). Steganographic generative adversarial networks. arXiv preprint arXiv:1703.05502. [Google Scholar] [Crossref]

6. https://scholar.google.com/scholar?q=Steganographic+Generative+Adversarial+Networks [Google Scholar] [Crossref]

7. Zhu, J., Kaplan, R., Johnson, J., & Fei-Fei, L. (2018). HiDDeN: Hiding data with deep networks. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 657–672). [Google Scholar] [Crossref]

8. https://scholar.google.com/scholar?q=HiDDeN+Hiding+Data+with+Deep+Networks [Google Scholar] [Crossref]

9. Zhang, K. A., Cuesta-Infante, A., Xu, L., & Veeramachaneni, K. (2019). SteganoGAN: High capacity image steganography with GANs. arXiv preprint arXiv:1901.03892. [Google Scholar] [Crossref]

10. https://scholar.google.com/scholar?q=SteganoGAN+High+Capacity+Image+Steganography+with+GANs [Google Scholar] [Crossref]

11. Boroumand, M., Chen, M., & Fridrich, J. (2019). Deep residual network for steganalysis of digital images. IEEE Transactions on Information Forensics and Security, 14(5), 1181–1193. [Google Scholar] [Crossref]

12. https://scholar.google.com/scholar?q=Deep+Residual+Network+for+Steganalysis+of+Digital+Images [Google Scholar] [Crossref]

13. Tabares-Soto, R., Orozco-Arias, S., Romero-Cano, V., Bucheli, V. S., & Jiménez-Varón, C. F. (2019). Deep learning applied to steganalysis of digital images: A systematic review. IEEE Access, 7, 68970–68990. [Google Scholar] [Crossref]

14. https://scholar.google.com/scholar?q=Deep+Learning+Applied+to+Steganalysis+of+Digital+Images+A+Systematic+Review [Google Scholar] [Crossref]

15. Duan, J., Jia, D., & Zhao, C. (2019). Reversible image steganography based on U-Net architecture. IEEE Access, 7, 160728–160742. [Google Scholar] [Crossref]

16. https://scholar.google.com/scholar?q=Reversible+Image+Steganography+Based+on+U-Net+Architecture [Google Scholar] [Crossref]

17. Chen, Y., Wang, H., & Liu, X. (2020). High-capacity robust image steganography based on adversarial networks. KSII Transactions on Internet and Information Systems, 14(8), 3382–3398. [Google Scholar] [Crossref]

18. https://scholar.google.com/scholar?q=High-Capacity+Robust+Image+Steganography+Based+on+Adversarial+Networks [Google Scholar] [Crossref]

19. Chen, Y., Xing, Z., & Liu, X. (2020). Technology of hiding and protecting secret image based on two-channel deep hiding network. IEEE Access, 8, 30325–30335. [Google Scholar] [Crossref]

20. https://scholar.google.com/scholar?q=Technology+of+Hiding+and+Protecting+Secret+Image+Based+on+Two-Channel+Deep+Hiding+Network [Google Scholar] [Crossref]

21. Zhou, X., Zhang, Y., & Wang, H. (2020). Security enhancement of image steganography using generative adversarial networks. IEEE Signal Processing Letters, 27, 1660–1664. [Google Scholar] [Crossref]

22. https://scholar.google.com/scholar?q=Security+Enhancement+of+Image+Steganography+Using+Generative+Adversarial+Networks [Google Scholar] [Crossref]

23. Manjula, G. R., & Sushma, R. B. (2021). Video steganography: A survey of techniques and methodologies. In Smart Data Intelligence 2021 (pp. 1–11). Springer, Singapore. [Google Scholar] [Crossref]

24. https://scholar.google.com/scholar?q=Video+Steganography+A+Survey+of+Techniques+and+Methodologies [Google Scholar] [Crossref]

25. Li, X., Wang, J., & Zhang, Y. (2021). Secure image steganography via generative adversarial networks. EURASIP Journal on Image and Video Processing, 2021(1), 1–15. [Google Scholar] [Crossref]

26. https://scholar.google.com/scholar?q=Secure+Image+Steganography+via+Generative+Adversarial+Networks [Google Scholar] [Crossref]

27. Wang, Y., & Chen, B. (2022). DWT–DCT based secure video steganography for multimedia communication. In Proceedings of the IEEE International Conference on Communication and Signal Processing (pp. 233–237). [Google Scholar] [Crossref]

28. https://scholar.google.com/scholar?q=DWT-DCT+Based+Secure+Video+Steganography+for+Multimedia+Communication [Google Scholar] [Crossref]

29. Wani, A., Sharma, S., & Gupta, R. (2022). Deep learning-based image steganography: A review. WIREs Data Mining and Knowledge Discovery, 12(6), e1481. [Google Scholar] [Crossref]

30. https://scholar.google.com/scholar?q=Deep+Learning-Based+Image+Steganography+A+Review [Google Scholar] [Crossref]

31. Rahman, M., Islam, M., & Hasan, M. (2022). Adaptive neural network-based image steganography for secure communication. Multimedia Tools and Applications, 81(24), 34987–35008. [Google Scholar] [Crossref]

32. https://scholar.google.com/scholar?q=Adaptive+Neural+Network-Based+Image+Steganography+for+Secure+Communication [Google Scholar] [Crossref]

33. Zhou, Y., Liu, J., & Wang, X. (2022). Encrypted image steganography using deep neural networks. IEEE Access, 10, 44281–44293. [Google Scholar] [Crossref]

34. https://scholar.google.com/scholar?q=Encrypted+Image+Steganography+Using+Deep+Neural+Networks [Google Scholar] [Crossref]

35. Mou, C., Xu, Y., Song, J., Zhao, C., Ghanem, B., & Zhang, J. (2023). Large-capacity and flexible video steganography via invertible neural network. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (pp. 1–10). [Google Scholar] [Crossref]

36. https://scholar.google.com/scholar?q=Large-Capacity+and+Flexible+Video+Steganography+via+Invertible+Neural+Network [Google Scholar] [Crossref]

37. Wang, H., Li, X., & Zhang, Y. (2023). Vision transformer-based image steganography for secure multimedia communication. Multimedia Tools and Applications, 82(15), 22847–22866. [Google Scholar] [Crossref]

38. https://scholar.google.com/scholar?q=Vision+Transformer-Based+Image+Steganography+for+Secure+Multimedia+Communication [Google Scholar] [Crossref]

39. Liu, Z., Chen, Y., & Zhao, H. (2023). Video transformer hiding framework for secure video steganography. Signal Processing: Image Communication, 112, 116934. [Google Scholar] [Crossref]

40. https://scholar.google.com/scholar?q=Video+Transformer+Hiding+Framework+for+Secure+Video+Steganography [Google Scholar] [Crossref]

41. Sousa, R. T., Silva, F., & Oliveira, L. (2024). Stego-STFAN: Spatial–temporal feature aggregation network for secure video steganography. Journal of Information Security and Applications, 78, 103612. [Google Scholar] [Crossref]

42. https://scholar.google.com/scholar?q=Stego-STFAN+Spatial-Temporal+Feature+Aggregation+Network+for+Secure+Video+Steganography [Google Scholar] [Crossref]

43. Alhamdani, A., Hassan, M., & Ahmed, R. (2025). DeepSteg: Deep learning-based video steganography with object tracking. Multimedia Systems, 31(2), 1–18. [Google Scholar] [Crossref]

44. https://scholar.google.com/scholar?q=DeepSteg+Deep+Learning-Based+Video+Steganography+with+Object+Tracking [Google Scholar] [Crossref]

45. Cheddad, A., Condell, J., Curran, K., & McKevitt, P. (2010). Digital image steganography: Survey and analysis of current methods. Signal Processing, 90(3), 727–752. https://doi.org/10.1016/j.sigpro.2009.08.010 [Google Scholar] [Crossref]

46. Fridrich, J., & Kodovský, J. (2012). Rich models for steganalysis of digital images. IEEE Transactions on Information Forensics and Security, 7(3), 868–882. [Google Scholar] [Crossref]

47. https://doi.org/10.1109/TIFS.2012.2190402 [Google Scholar] [Crossref]

48. Kheddar, H., Hemis, M., Himeur, Y., Megías, D., & Amira, A. (2024). Deep learning for steganalysis of diverse data types: A review of methods, taxonomy, challenges and future directions. Neurocomputing, 587, 127588. [Google Scholar] [Crossref]

49. https://doi.org/10.1016/j.neucom.2024.127588 [Google Scholar] [Crossref]

50. Liu, S., Zhang, H., Zhao, Y., & Wang, J. (2023). Video steganography: Recent advances and challenges. Multimedia Tools and Applications, 82(27), 41943–41985. [Google Scholar] [Crossref]

51. https://doi.org/10.1007/s11042-023-15158-0 [Google Scholar] [Crossref]

52. Luo, X., Liu, F., Lian, S., et al. (2021). Deep learning-based steganography and steganalysis: A survey. ACM Computing Surveys, 54(2), 1–36. [Google Scholar] [Crossref]

53. https://doi.org/10.1145/3437479 [Google Scholar] [Crossref]

54. Weng, X., Li, Y., Chi, L., & Mu, Y. (2018). Convolutional video steganography with temporal residual modeling. In L. Leal-Taixé & S. Roth (Eds.), ECCV 2018 Workshops (LNCS Vol. 11134, pp. 237–253). Springer, Cham. [Google Scholar] [Crossref]

55. https://doi.org/10.1007/978-3-030-11021-5_18 [Google Scholar] [Crossref]

56. Zhang, R., Zhu, H., Liu, F., & Liu, J. (2024). Video steganography based on deep convolutional neural networks. Multimedia Tools and Applications, 83(4), 10357–10378. [Google Scholar] [Crossref]

57. https://doi.org/10.1007/s11042-023-17158-6 [Google Scholar] [Crossref]

• Enhancing Formation Control of Multi Agent Systems Using Ann Based Technique
• Improving Sliding Mode Control with Chattering Reduction using Fuzzy Based Technique
• Cooking Quality, Fasting Blood Glucose, Glycemic Index and Load of High–Fiber Noodles Made from Wheat, Tiger Nut Residue and Cassava Flour Blends
• Matrix Rhythm Therapy Versus Interferential Therapy Combined with Lumbar Stabilization Exercises in Chronic Non-Specific Low Back Pain: A Randomized Comparative Trial
• Formulation and Sensory Evaluation of Functional Cake Prepared from Sweet Potato Powder