Abstract—Neural cryptography is based on synchronization of tree parity machines by mutual learning. We extend previous key-exchange protocols by replacing random inputs with queries depending on the current state of the neural networks. The results show that queries restore the security against attackers. We further restrict amount information available to an attacker by keeping seed of pseudo randomnumber generator private.
Index Terms—Neural cryptography, query, mutual learning,tree parity machine, neural synchronization, encryption/decryption.
Pravin Revankar and W. Z. Gandhare are with the Government College of Engineering, Aurangabad, India. (email: prevankar@gmail.com, wz_gandhare@yahoo.com).
Dilip Rathod is with the Dept. of Information Technology, P. E. S. College of Engineering, Aurangabad, India (email: rathod.dt@gmail.com).
Cite: Pravin Revankar, W. Z. Gandhare and Dilip Rathod, "Private Inputs to Tree Parity Machine," International Journal of Computer Theory and Engineering vol. 2, no. 4, pp. 665-669, 2010.
Copyright © 2008-2024. International Association of Computer Science and Information Technology. All rights reserved.
