Design of S-boxes based on neural networks*

In this paper, we present a framework for the design of S-boxes used in ciphers based on neural networks. It can yield S-boxes with different input and output length. The designed n × n S-boxes satisfy the desired cryptographic properties of non-linearity, completeness, strict avalanche, and output bits independence criteria. We propose a four layer topology, where the number of neurons, located at the input layer, is two times the number of input bits of the designed S-box and also, the number of neurons, located at the first hidden layer, is as equal as input layer neurons, while its second hidden layer included n/2 neurons, and its output layer included n neurons. The input value of the designed S-boxes consists of n-bit input vector and constant n-bit initial value (IV). We apply a Sigmoid nonlinear function as the activation function of our scheme. The values of weights were obtained through error back propagation learning algorithm, while a training set is used for learning. The used training set consists some different pairs of plaintexts and ciphertexts with AES's S-box. We also implement an 8 × 8 S-box based on neural networks with the essential security criteria. The results indicate that the proposed scheme can yield S-boxes with the desired cryptographic properties.

[1]  L.C. De Silva,et al.  Application of multilayer perceptron networks in symmetric block ciphers , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[2]  Babak Sadeghiyan,et al.  Finding the differential characteristics of block ciphers with neural networks , 2008, Inf. Sci..

[3]  William Millan,et al.  How to Improve the Nonlinearity of Bijective S-Boxes , 1998, ACISP.

[4]  John B. Kam,et al.  Structured Design of Substitution-Permutation Encryption Networks , 1979, IEEE Transactions on Computers.

[5]  Donghui Guo,et al.  A New Symmetric Probabilistic Encryption Scheme Based on Chaotic Attractors of Neural Networks , 2004, Applied Intelligence.

[6]  Shiguo Lian,et al.  Secure hash function based on neural network , 2006, Neurocomputing.

[7]  Carlos A. Paz de Araujo,et al.  A Neural Key Generator for a Public Block Cipher , 2006, 2006 Ninth Brazilian Symposium on Neural Networks (SBRN'06).

[8]  D. Pointcheval.  Neural Networks and their Cryptographic Applications , 1994 .

[9]  Jennifer Seberry,et al.  Fundamentals of Computer Security , 2003, Springer Berlin Heidelberg.

[10]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[11]  Lee-Ming Cheng,et al.  The convergence properties of a clipped Hopfield network and its application in the design of keystream generator , 2001, IEEE Trans. Neural Networks.

[12]  Wolfgang Kinzel,et al.  Neural cryptography , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[13]  L.C. De Silva,et al.  Application of MultiLayer Perceptron Network as a one-way hash function , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[14]  Shiguo Lian,et al.  Multimedia Content Protection Based on Chaotic Neural Networks , 2007, Computational Intelligence in Information Assurance and Security.

[15]  Shujun Li,et al.  Chosen-Plaintext Cryptanalysis of a Clipped-Neural-Network-Based Chaotic Cipher , 2004, ISNN.

[16]  Luigi M. Ricciardi,et al.  Diffusion models of neuron activity , 1998 .

[17]  Stafford E. Tavares,et al.  On the Design of S-Boxes , 1985, CRYPTO.

[18]  A. Sadeghian,et al.  On the use of recurrent neural networks to design symmetric ciphers , 2008, IEEE Computational Intelligence Magazine.

[19]  Shiguo Lian,et al.  A block cipher based on chaotic neural networks , 2009, Neurocomputing.

[20]  Xiaofeng Liao,et al.  A Combined Hash and Encryption Scheme by Chaotic Neural Network , 2004, ISNN.

[21]  Jui-Cheng Yen,et al.  Design and realization of a new chaotic neural encryption/decryption network , 2000, IEEE APCCAS 2000. 2000 IEEE Asia-Pacific Conference on Circuits and Systems. Electronic Communication Systems. (Cat. No.00EX394).