Security in Voip Network Using Neural Network and Encryption Techniques

Voice over Internet Protocol is one of the fastest growing applications. Since VoIP networks are very much vulnerable to attacks, providing security in such networks is a matter of great concern. For secure communication in VoIP network, authentication and integrity of messages must be provided. In this paper, we use a remote password authentication scheme for multi-server environments. The password authentication system is a pattern classification system based on artificial neural network. In this scheme, the users only remember user identity and password numbers to log in to various servers. Users can freely choose their password. Furthermore, the system is not required to maintain a verification table and can withstand the replay attack. For integrity of messages, we use modified AES algorithm in which it will be able to accept variable length packets for encryption and decryption.