A Novel Cryptographic Scheme Based on Wavelet Neural Networks
Part of the
Lecture Notes in Computer Science
book series (LNCS, volume 3973)
A novel method for encryption based on a wavelet neural network (WNN) is presented. The WNN is trained by a heuristic algorithm and can generate a random sequence which is used for encrypting and decrypting. Furthermore, some simulated experiments, including key space analysis, key sensitivity test, statistical analysis, are performed to substantiate that our scheme can make cipher-text more confusion and diffusion and that the method can resist several attacks, effectively.
KeywordsChaotic System Chaotic Sequence Cipher Image Wavelet Neural Network Hide Layer Node
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Shneier, B.: Applied Cryptography: Protocols Algorithms, and Source Code in C. John Wiley & Sons, Inc., Chichester (1996)Google Scholar
Shannon, C.E.: Communication Theory of Secrecy Systems, Bell Systems. Technical Journal 28, 656–715 (1949)MATHMathSciNetGoogle Scholar
Szu, H., Telfer, B., et al.: Neural Network Adaptive Wavelets for Signal Representation and Classification. Optical Engineering 36, 1907–1916 (1992)CrossRefGoogle Scholar
Simon, H.: Neural Network a Comprehensive Foundation. Prentice Hall, Inc., Englewood Cliffs (1999)Google Scholar
Van Ooyen, A., Nienhuis, B.: Improving the Convergence of Back Propagation Algorithm. Neural Networks 5, 465–471 (1992)CrossRefGoogle Scholar
Kohda, T., Tsuneda, A.: Statistics of Chaotic Binary Sequences. IEEE Transactions on Information Theory 43, 104–112 (1997)MATHCrossRefMathSciNetGoogle Scholar
© Springer-Verlag Berlin Heidelberg 2006