Image Steganography Using Deep Neural Networks


Reddy Madhavi K.1, PhD, K. Pranitha2, M. Tech, Nagendar Yamsani3, M. Tech, Mohmad Ahmed Ali4, M. Tech, K. Srujan Raju5, PhD and Balijapalli Prathyusha6, B. Tech
1School of Computing, Mohan Babu University, Tirupati, India
2B.V. Raju Institute of Technology, Narsapur, Medak, Telangana, India
3Assistant Professor, School of Computer Science and Artificial Intelligence, SR University, Warangal, India
4Associate Professor, Department of CSE, CMR Institute of Technology, Hyderabad, Telangana, India
5Professor, Department of CSE, CMR Technical Campus, Hyderabad, Telangana, India
6UG Scholar, CSE. Sree Vidyanikethan Engineering College, Tirupati, A.P., India

Part of the book: Information and Knowledge Systems
Chapter DOI:


Steganography involves the use of hiding a secret or unknown message in a regular message. Steganography is commonly used in such a way that smaller messages are difficult to detect within a larger image’s noisy areas. In this chapter, we try to fit a color image in another image which is of the same size. Deep Neural Networks (DNN) are trained to simultaneously produce the concealing and disclosing activities in a pair-wise fashion. The system is tested on real-world photos from a range of sources and was trained on images chosen at random from the ImageNet collection. Beyond illustrating how deep learning may be used to successfully hide images, we closely study the process and consider extensions. Many methods such as Least Significant Bit (LSB), Highly Undetectable steGO (HUGO), Wavelet Obtained Weights (WOW) are effective for image steganography but they encrypt the secret message in the carrier image’s Least Significant Bits, in contrast to the Deep Neural Network method, which compacts and spreads the representation of the secret image throughout all of the available bits. Without being expressly instructed to do so, the deep neural network algorithm examines the data for features that correlate and combine them to support learning in a faster way. This is the most advanced technique which is used for the image steganography.

Keywords: steganography, LSB, HUGO, WOW, deep neural networks


Baluja, Shumeet. “Hiding images within images.” IEEE transactions on pattern analysis and machine intelligence 42, no. 7 (2019): 1685-1697.

Chandhan, Madhavarapu, K. Reddy Madhavi, U. Ganesh Naidu, and Padmavathi Kora. “A NOVEL GEOTAGGING METHOD USING IMAGE STEGANOGRAPHY AND GPS.” Turkish Journal of Physiotherapy and Rehabilitation (2020) 32: 3.

Duan, Xintao, Kai Jia, Baoxia Li, Daidou Guo, En Zhang, and Chuan Qin. “Reversible image steganography scheme based on a U-Net structure.” IEEE Access 7 (2019): 9314-9323.

Jiang, Kui, Zhongyuan Wang, Peng Yi, and Junjun Jiang. “Hierarchical dense recursive network for image super-resolution.” Pattern Recognition 107 (2020): 107475.

Kreuk, Felix, Yossi Adi, Bhiksha Raj, Rita Singh, and Joseph Keshet. “Hide and speak: Towards deep neural networks for speech steganography.” arXiv preprint arXiv:1902.03083 (2019).

Luo, Yuling, Xue Ouyang, Junxiu Liu, and Lvchen Cao. “An image encryption method based on elliptic curve elgamal encryption and chaotic systems.” IEEE Access 7 (2019): 38507-38522.

Lu, Wei, Yingjie Xue, Yuileong Yeung, Hongmei Liu, Jiwu Huang, and Yun-Qing Shi. “Secure halftone image steganography based on pixel density transition.” IEEE Transactions on Dependable and Secure Computing 18, no. 3 (2019): 1137-1149.

Rasras, Rashad J., Ziad A. AlQadi, and Mutaz Rasmi Abu Sara. “A methodology based on steganography and cryptography to protect highly secure messages.” Engineering, Technology & Applied Science Research 9, no. 1 (2019): 3681-3684.

Sahu, Aditya Kumar, and Gandharba Swain. “Dual stego-imaging based reversible data hiding using improved LSB matching.” International Journal of Intelligent Engineering and Systems 12, no. 5 (2019): 63-73.

Sunitha, Gurram. “Intelligent System to Find the Health Care Centers for Senior Citizens Based on Disease and Nearest Locations using GPS.” Turkish Journal of Computer and Mathematics Education (TURCOMAT) 12, no. 2 (2021): 2140-2150.

Xiao, Yi, Xinqing Wang, Peng Zhang, Fanjie Meng, and Faming Shao. “Object detection based on faster R-CNN algorithm with skip pooling and fusion of contextual information.” Sensors 20, no. 19 (2020): 5490.


Publish with Nova Science Publishers

We publish over 800 titles annually by leading researchers from around the world. Submit a Book Proposal Now!