A Novel Image Encryption Algorithm Based on Hybrid Chaotic Mapping and Intelligent Learning in Financial Security System
With the expansion and prevalence of financial certification, problems of financial security have been springing up. How to ensure the security of financial information and protect our privacy is an issue of particular concern. In order to reduce the influence of chaotic periodicity on cipher-text,...
Gespeichert in:
Veröffentlicht in: | Multimedia tools and applications 2020-04, Vol.79 (13-14), p.9163-9176 |
---|---|
Hauptverfasser: | , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | With the expansion and prevalence of financial certification, problems of financial security have been springing up. How to ensure the security of financial information and protect our privacy is an issue of particular concern. In order to reduce the influence of chaotic periodicity on cipher-text, an image dynamic encryption algorithm based on hybrid chaotic system and deep network is proposed in this paper. Firstly, the hybrid chaotic system is constructed to combine many mapping functions by using the nonlinear combination mechanism, and the chaotic sequence is outputted to generate the initial value of hybrid chaotic system by using the pixel value. Then the plain-text pixel values are adopted to generate the initial value of the hybrid system for improving the anti-plain attack ability of the algorithm; Artificial neural network is used to process chaotic sequences, and effectively eliminate chaotic periodicity; The classification and encryption of permutation image are realized by constructing quantization method and hetero-diffusion technology. The experimental results show that our proposed encryption technology has higher security and stronger ability to resist plain-text attack compared with the existing image encryption algorithms, which adapts to enhance the security of the financial system. |
---|---|
ISSN: | 1380-7501 1573-7721 |
DOI: | 10.1007/s11042-018-7144-5 |