Hash function generation by neural network

Abstract

Effective generation of hash function is very important for an achievement of a security of today networks. A cryptographic hash function is a transformation that takes an input and returns a fixed-size value, which is called the hash value. An artificial neural network (ANN), as a possible approach, could be used for the hash function generation. The performance of the ANN was validated by software implementation of ANN for given network configuration. The principles of artificial neural networks and the possibility of using artificial neural network for hashing are presented in the article. For analysis of ANN were created testing sets on the base of several examples of general texts in English and in Slovak language. In the paper were tested ANNs with one hidden layer. The number of neurons in the hidden layer of the artificial neural network is optimized based on the results in the simulation.