Comparative Analysis of Artificial Neural Network Statistical Parameters and Novel Techniques for Data Encryption and Decryption, Distribution, and Estimation
Sphinx Journal of Mathematical Sciences · 2026
DOI: 10.64389/sjms.2026.012127 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sphinx Journal of Mathematical Sciences, 2026. Verfasst von Samah Mohamed und 4 weiteren Autor:innen.
Abstract (Originalsprache)
The use of statistical metrics to compare the application of several unique communication techniques that rely on a certain system is the foundation of this paper. By making it more difficult for attackers to anticipate patterns and the speed of the encryption and decryption processes, this technology protects communication routes. When compared to solutions using mathematical techniques, the employment of artificial neural networks (ANN) in data encryption and decryption, such as communications, demonstrates that the test patterns of cryptographic messages in our collection displayed a shorter decryption time. This study's methodology can be successfully applied to lengthy communications, where it is difficult and time-consuming to apply mathematical methods for encryption and decryption. We present various measures of fitting goodness to the ANN method in order to reach the most preferred distribution to analyses our results, along with the benefits and drawbacks of both approaches in terms of security level, encryption and decryption time, and speed of use.
Zitieren
APA
Mohamed, S., Gaballah, A. S., Osman, E. S., Haggag, A., & Elsharkawy, K. (2026). Comparative Analysis of Artificial Neural Network Statistical Parameters and Novel Techniques for Data Encryption and Decryption, Distribution, and Estimation. Sphinx Journal of Mathematical Sciences. https://doi.org/10.64389/sjms.2026.012127
Vancouver
Mohamed S, Gaballah AS, Osman ES, Haggag A, Elsharkawy K. Comparative Analysis of Artificial Neural Network Statistical Parameters and Novel Techniques for Data Encryption and Decryption, Distribution, and Estimation. Sphinx Journal of Mathematical Sciences. 2026. doi:10.64389/sjms.2026.012127
BibTeX
@article{Mohamed2026,
author = {Mohamed, Samah and Gaballah, Ali Saad and Osman, Eman Said and Haggag, Ayman and Elsharkawy, Khaled},
title = {Comparative Analysis of Artificial Neural Network Statistical Parameters and Novel Techniques for Data Encryption and Decryption, Distribution, and Estimation},
journal = {Sphinx Journal of Mathematical Sciences},
year = {2026},
doi = {10.64389/sjms.2026.012127}
}
EUVIMED