Title
A block image encryption algorithm based on a hyperchaotic system and generative adversarial networks
Abstract
To address the problems of existing image encryption algorithms based on chaotic systems, such as the weak resistance to attack, the unstable performance of the chaotic system, and the small size of the key space, a new block image encryption algorithm based on a new hyperchaotic system and generative adversarial networks (GANs) is proposed in this paper. First, a new hyperchaotic system with an improved chaotic dynamic performance and key space is designed. Then, to ensure the security and efficiency of whole-image block encryption, the new hyperchaotic system is combined with the nonlinear parallel processing mechanism of the neural network, key stream, generative adversarial networks and an improved generalized Feistel structure to scramble and diffuse the plaintext image at the pixel level to obtain the ciphertext image. The experimental results show that the proposed encryption algorithm has a large key space, high security and robustness and resistance to common attacks. At the same time, the proposed method provides a new idea for the combination of chaotic systems and neural networks in image encryption.
Year
DOI
Venue
2022
10.1007/s11042-022-12092-y
Multimedia Tools and Applications
Keywords
DocType
Volume
Hyperchaotic system, Generative adversarial networks, Block image encryption
Journal
81
Issue
ISSN
Citations 
15
1380-7501
0
PageRank 
References 
Authors
0.34
23
4
Name
Order
Citations
PageRank
Pengfei Fang100.34
Han Liu200.34
Chengmao Wu300.34
Min Liu433540.49