Combination of biometric data and learning algorithms for both generation and application of a secure communication link

We describe a novel secure communication system (SCS) via public networks. For the generation of a unique pair of encryption module (EM) and decryption module (DM), learning algorithms are applied in combination with biometric data of the future DM-user. Subsequently, EM can be attached to any comp uter to form a generally usable encryption unit (EU) while DM, if attached to another computer to form the matching decryption unit (DU), can only be activated by the specific pair-generating DM-user. EU transforms spatial data to temporal data by means of spatio-temporal (ST) filters. DU uses a combination of analytical- and learning algorithms for decryption.