A Novel Approach for Password Authentication Using Bidirectional Associative Memory

TL;DR

This paper introduces a new password authentication method using Bidirectional Associative Memory that supports both text and graphical passwords, enhancing security by converting passwords into probabilistic values.

Contribution

The paper proposes a novel BAM-based password authentication system that handles both character and image passwords, improving security over traditional methods.

Findings

Conversion of passwords into probabilistic values enhances security.

The BAM-based system successfully authenticates both text and image passwords.

Test results demonstrate improved security features of the proposed method.

Abstract

Password authentication is a very important system security procedure to gain access to user resources. In the Traditional password authentication methods a server has check the authenticity of the users. In our proposed method users can freely select their passwords from a predefined character set. They can also use a graphical image as password. The password may be a character or an image it will be converted into binary form and the binary values will be normalized. Associative memories have been used recently for password authentication in order to overcome drawbacks of the traditional password authentication methods. In this paper we proposed a method using Bidirectional Associative Memory algorithm for both alphanumeric (Text) and graphical password. By doing so the amount of security what we provide for the user can be enhanced. This paper along with test results show that converting user password in to Probabilistic values and giving them as input for BAM improves the security of the system