The theory of neural networks and cryptography

A connection between the theory of neural networks and cryptography is presented. A new phenomenon namely synchronization of neural networks is leading to a new method of exchange of secret messages. Two articial networks being trained by the Hebbian learning rule on their mutual outputs develop an antiparallel state of their synaptic weights. The synchronized weights are used to construct an ephemeral key exchange protocol for the secure transmission of secret data. The complexity of the generation of the secure channel is linear with the size of the network. An attacker who knows the protocol and all details of any transmission of the data nds it difficult to decrypt the secret message.