Improving ability of passive attacks of chaotic encryption by using neural network

Abstract

Chaotic encryption have been widely studied and applied in cryptology field because its good randomicity and sensitivity to initial value. But nowadays it can't effectively defend passive attacks from outer world under development of hi-tech. Neural network be used into chaotic algorithm for its mnemonic function and self-study function can improve anti-passive-attacks ability of chaotic security system. This method can change length of secret-key at will also, which made the security system more flexible and practical. © Springer-Verlag Berlin Heidelberg 2005.