Master Assignment
Digital media - using neural networks for steganography
Type: Master EE/CS
Period: TBD
Student: (Unassigned)
If you are interested please contact :
Description:
Hiding media inside media while preserving the perceptual information is challenging and has become a hot topic in computer vision and information security. In this project, the student is meant to understand the field and develop a new framework for image-based steganography relying on deep networks.
The supervision will come from both fields. For further details you can contact Estefania Talavera (DMB - e.talaveramartinez@utwente.nl) and Dipti K. Sarmah (SCS - d.k.sarmah@utwente.nl).
Relevant reads:
- Yang, Hyukryul, et al. "Hiding video in audio via reversible generative models." Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019.
- Lu, Shao-Ping, et al. "Large-capacity image steganography based on invertible neural networks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021.
- Das, Abhishek, et al. "Multi-image steganography using deep neural networks." arXiv preprint arXiv:2101.00350 (2021).
- Sarmah, D.K., Kulkarni, A.J. (2018): “JPEG based Steganography Methods using Cohort Intelligence with Cognitive Computing and Modified Multi Random Start Local Search Optimization Algorithms”, Information Sciences, 430-431, PP 378-396.
- Sarmah, D.K., Kulkarni, A.J. (2019): “Improved Cohort Intelligence-a High Capacity, Swift and Secure Approach on JPEG image Steganography”, Journal of Information Security and Applications, 45, pp 90-106.