3D chaos graph deep learning method to encrypt and decrypt digital image

Daniah Abdul Qahar Shakir, Ali Jbaeer Dawood


We live in technological age development’s where many important data transmitted electronically from one device to another and in every place. Deep learning algorithms have facilitated the process of encoding and decoding digital images. Chaotic graph systems, on the other hand, are one of the most recent techniques utilized to encode image data based on the methods of cryptography. The chaos maps are divided into two main aspects, first one deals with the 1D map which requires fewer features and can be developed easily, the second one is the high dimensional map which is more complex than the 1D graph and it requires more features, more parameters, and it is relatively hard to develop. In this paper, we present a method for image encoding and decoding electronically using deep learning, the proposed algorithm was developed by using the hybrid technique of 3D chaos map generation, the best case of the proposed technique gave the following results: The average entropy calculation was (7.4838) before image encryption and (7.9896) after image encryption with average number of pixels change rate (NPCR) of (99.7085%) and the unified average changing intensity (UACI) of (33.2030%) which are the best outcomes when compared to other similar works.


3D chaos map; Decryption; Deep learning; Digital images; Encryption; Multimedia;

Full Text:


DOI: http://doi.org/10.11591/ijeecs.v25.i2.pp941-951


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Indonesian Journal of Electrical Engineering and Computer Science (IJEECS)
p-ISSN: 2502-4752, e-ISSN: 2502-4760
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).

shopify stats IJEECS visitor statistics