Regensburg 2007 – scientific programme
Parts | Days | Selection | Search | Downloads | Help
DY: Fachverband Dynamik und Statistische Physik
DY 2: Time-delayed feedback and neural networks
DY 2.6: Talk
Monday, March 26, 2007, 11:45–12:00, H3
Dynamics of neural cryptography — •Andreas Ruttor1, Ido Kanter2, and Wolfgang Kinzel1 — 1Institut für Theoretische Physik, Universität Würzburg, Am Hubland, 97074 Würzburg — 2Minerva Center and Department of Physics, Bar Ilan University, Ramat Gan 52900, Israel
Synchronization of neural networks has been used for novel public channel protocols in cryptography. In the case of Tree Parity Machines the dynamics of both bidirectional synchronization and unidirectional learning is driven by attractive and repulsive stochastic forces. Thus it can be described well by a random walk model for the overlap between participating neural networks. For that purpose transition probabilities and scaling laws for the step sizes are derived analytically. Both these calculations as well as numerical simulations show that bidirectional interaction leads to full synchronization on average. In contrast, successful learning is only possible by means of fluctuations. Consequently, synchronization is much faster than learning, which is essential for the security of the neural key-exchange protocol.