Neural cryptography

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.

[1]  Wolfgang Kinzel,et al.  Cryptography based on neural networks—analytical results , 2002 .

[2]  I Kanter,et al.  Generation of unpredictable time series by a neural network. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[3]  Wolfgang Kinzel,et al.  Mutual learning in a tree parity machine and its application to cryptography. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[4]  W. Kinzel,et al.  Secure exchange of information by synchronization of neural networks , 2002 .

[5]  I Kanter,et al.  Interacting neural networks. , 2000, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[6]  Franklin A. Graybill,et al.  Introduction to The theory , 1974 .

[7]  Adi Shamir,et al.  Analysis of Neural Cryptography , 2002, ASIACRYPT.

[8]  Douglas R. Stinson,et al.  Cryptography: Theory and Practice , 1995 .

[9]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.