Neural network based decryption for random encryption algorithms

Typically encryption follows a specific rule with or without a key so that the cipher text can be decoded using the corresponding suitable decryption algorithm. This paper aims at removing the need for the encoding to follow a general rule by using a neural network for decoding the cipher text. Hence introducing the randomness in coding making it so much more difficult to decode. We have also introduced the concept of including lies in the information transmitted to misguide any eavesdropper who manages to decipher the cipher text. The presented results are obtained through the use of MATLAB 7.0.1.