Abstract |
Neural networks can synchronize by learning from each other. In the case of discrete weights full synchronization is achieved in a finite number of steps. Additional networks can be trained by using the inputs and outputs generated during this process as examples. Several learning rules for both tasks are presented and analyzed. In the case of Tree Parity Machines synchronization is much faster than learning. Scaling laws for the number of steps needed for full synchronization and successful learning are derived using analytical models. They indicate that the difference between both processes can be controlled by changing the synaptic depth. In the case of bidirectional interaction the synchronization time increases proportional to the square of this parameter, but it grows exponentially, if information is transmitted in one direction only. Because of this effect neural synchronization can be used to construct a cryptographic key-exchange protocol. Here the partners benefit from mutual interaction, so that a passive attacker is usually unable to learn the generated key in time. The success probabilities of different attack methods are determined by numerical simulations and scaling laws are derived from the data. They show that the partners can reach any desired level of security by just increasing the synaptic depth. Then the complexity of a successful attack grows exponentially, but there is only a polynomial increase of the effort needed to generate a key. Further improvements of security are possible by replacing the random inputs with queries generated by the partners. |