Neuro-Genetic based Speech Processing for Promoting Global Cyber Security using Steganography technique

Abstract

The goal of cryptography is to provide confidentiality and privacy by encrypting the information. If any unauthorized human body does cryptanalysis then this goal may be defeated. In this paper the authors have attempted an algorithm called STEG_NGBSP (steganography/neuro-genetic based speech processing) using a technique called steganography that inherits some features of cryptography in such a way, that the information is encrypted as well as hidden. The methodology adopted here is the concept of null ciphers, which are extracted from the speech signal of a Bengali speaker using neuro-genetic approach. The speech signal is processed and then veiled with an image. Every image is encapsulated with some information, which may be decrypted at the receivers end using the master image-voiced frame, in which the speech data is covered by another image. The proposed algorithm is unique in handling the security measures from steganalysis, thus promoting global cyber security and bridging the gap between the computer and the user with more security through natural language processing