Performance Evaluation of Password Authentication using Associative Neural Memory Models

Abstract

They are many ways of providing security to user resources. Password authentication is a very important system security procedure to secure user resources. In order to solve the problems with traditional password authentication several methods have been introduced to provide password authentication using Associative Memories like Back Propagation Neural Network (BPNN),Hopfield Neural Network(HPNN),Bidirectional Associative Memories(BAM),Brain-State-in-a Box(BSB). Later Password authentication has been provided using Context-Sensitive Associative Memory Method (CSAM). Here in this paper we proposed performance analysis of password authentication schemes using Associative memories and CSAM using graphical Images. We observe that in comparison to existing layered and associative neural network techniques for graphical images as password, the CSAM method provides better accuracy and quicker response time to registration and password changes.