International Journal of Engineering Applied Sciences and Technology, 2020 Vol. 5, Issue 1, ISSN No. 2455-2143, Pages 26-29 Published Online May 2020 in IJEAST (http://www.ijeast.com) 26 IMPROVING THE EFFICIENCY OF DES ALGORITHM USING NEURAL NETWORKS Yousif Elfatih Yousif Department of Computer Engineering Faculty of Engineering, Alzaiem Alazhari University, Khartoum, Sudan Abstract— Cryptography is the technique of changing data or information into unreadable for unauthorized persons. In cryptography process information transfer from sender to receiver in a manner that prevents from unauthorized third person. There are so many cryptography methods are available which based on number theory. An Artificial Neural Network (ANN) have many characteristics such as learning, generation, less data requirement, fast computation, ease of implementation and software and hardware availability. It is very useful for many applications, in this paper we explore the implementation of DES cryptography algorithm using ANN to reduce the execution time. this paper provides comparison between normal DES and ANN DES. Keywords— Cryptography, Artificial Neural Network, execution time, DES I. INTRODUCTION A neural network is a parallel distributed processor which is made up of simple processing units. These units have a natural propensity to store the experimental knowledge and making it available for use. Work on artificial neural networks, commonly referred to as “neural networks “has been motivated right from its inception by the recognition that human brain computes in an entirely different way from the conventional digital computer. An artificial neural network, which is the formal name for the term neural networks used here, is one of many attempts to build an intelligent machine or to create artificial intelligence. It is based on biological neural networks. The basic idea to model this is to make a very simplified model of biological neurons and their synapses. [1] Cryptography is a technique to hide the data over communication channel. The developed tangible and hardware tools are not Sufficient to protect the data from unauthenticated parties. Therefore, the experts, researchers and developers have to build and develop security systems, protect the information and prevent the attackers from playing with the very important source (information). For this reason, the term "Encryption/Decryption" was brought out, and it is the main factor that should be available in protection system and take for a real process to manipulate and generate the security system. It is an art to hide the data to strangers. As the technology grows day by day the need of data security over communication channel is increased to high extent. For securing the knowledge cryptography is used, and this cryptosystem can be distinguished in two major types: Secrete-Key Cryptography and Public Key Cryptography. the Secret key cryptography includes DES, AES, 3DES, IDEA, Blowfish algorithms etc. and public key cryptography includes RSA, DIGITAL SIGNATURE AND MESSAGE Digest algorithms. Now a days computer networks are becoming more important for exchanging information. One of the most important requirements of these networks is to provide secure transmission of information from one place to another. Cryptography is one of the techniques which provide most secure way to transfer the sensitive information from sender to intended receiver [2]. II. METHODOLOGY This paper is improving Performance of DES algorithm using an Artificial Neural Network, sophisticated implementation has been made with An Artificial Neural Network (ANN) for encrypting and decrypting of data. also designing and analyzing for the performance of Proposed technique was made and it compared to the normal technique in the MATLAB simulator environment, also this study was provided evaluation for two methods. III. DATA ENCRYPTION STANDARD (DES) DES is a block cipher. It encrypts the data in a block of 64 bits. It produces 64 bit cipher text. The key length is 56 bits. Initially the key is consisting of 64 bits. The bit position 8, 16, 24, 32,40,48,56, 64 discarded from the key length [3]. Fig. 1 The DES steps