To search, Click below search items.


All Published Papers Search Service


Classification of Substitution Ciphers using Neural Networks


G.Sivagurunathan, V.Rajendran, T.Purusothaman


Vol. 10  No. 3  pp. 274-279


Most of the time of a cryptanalyst is spent on finding the cipher technique used for encryption rather than the finding the key/ plaintext of the received cipher text. The Strength of the classical substitution cipher’s success lie on the variety of characters employed to represent a single character. More, the characters employed more the complexity. Thus, in order to reduce the work of the cryptanalyst, neural network based identification is done based on the features of the cipher methods. In this paper, classical substitution ciphers, namely, Playfair, Vigen?re and Hill ciphers are considered. The features of the cipher methods under consideration were extracted and a backpropagation neural network was trained. The network was tested for random texts with random keys of various lengths. The cipher text size was fixed as 1Kb. The results so obtained were encouraging.


Cipher text, Classifier, Back propagation neural network, Playfair cipher, Hill Cipher, Vigen?re cipher