Title :
Neural cryptography
Author :
Kinzel, Wolfgang ; Kanter, I.
Author_Institution :
Inst. for Theor. Phys., Wurzburg Univ., Germany
Abstract :
Two neural networks which are trained on their mutual output bits show a novel phenomenon: The networks synchronize to a state with identical time dependent weights. It is shown how synchronization by mutual learning can be applied to cryptography: secret key exchange over a public channel.
Keywords :
learning (artificial intelligence); neural nets; public key cryptography; synchronisation; trees (mathematics); mutual learning; neural cryptography; neural networks; public channel; secret key exchange; secret message transmission; synchronization; tree parity machine; Cryptography; Differential equations; Multi-layer neural network; Neural networks; Physics;
Conference_Titel :
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN :
981-04-7524-1
DOI :
10.1109/ICONIP.2002.1202841
