Information theoretic approach for decipherment problems is the recent trend in cryptanalysis. The behavioral transformation of message units is addressed upto certain extent in the encryption process. However the amount of confusion and diffusion in terms of statistical distribution parameters between message and cipher text is a point of interest for cryptanalyst. In the present work we addressed this issue with the help of enhanced probability distribution function. The basic units of any message text are observed to be heuristic in nature depending on the sample. Averaging function is adopted while evaluating the enhanced probabilities of message units. The retrieved efficiency of cipher text only attack on samples of English, Hindi Telugu, Kannada is presented in this paper.

This paper shows the possibility of exploiting the features of Genetic Algorithm with poly substitution methods in a linear way, to generate ASCII values of the given text and then applying conversion, transposition with the features of Cryptography. In polyalphabetic substitution ciphers the plaintext letters are enciphered differently depending upon their placement in the text. As the name polyalphabetic suggests this is achieved by using several two, three keys and random keys combinations instead of just one, as is the case in most of the simpler crypto systems. Using two keys, we take 2 keys e1,e2 and let the ASCII values of e1 be 1 and e2 be 2 and take the text, add ASCII values of e1 to first character and ASCII values of e2 to second character. Alternatively add the value of e1 and e2 to consecutive characters. We can use Poly substitution method combining the features of cryptography for text encryption by 2 keys and 3 keys and even more then 3 keys to make the decryption process more complicated. Key words