## Abstract

The security of neural cryptography is investigated. A key-exchange protocol over a public channel is studied where the parties exchanging secret messages use multilayer neural networks which are trained by their mutual output bits and synchronize to a time dependent secret key. The weights of the networks have integer values between [formula presented] Recently an algorithm for an eavesdropper which could break the key was introduced by [A. Shamir, A. Mityagin, and A. Klimov, Ramp Session (Eurocrypt, Amsterdam, 2002)]. We show that the synchronization time increases with [formula presented] while the probability to find a successful attacker decreases exponentially with L. Hence for large L we find a secure key-exchange protocol which depends neither on number theory nor on injective trapdoor functions used in conventional cryptography.

Original language | English |
---|---|

Pages (from-to) | 5 |

Number of pages | 1 |

Journal | Physical Review E |

Volume | 66 |

Issue number | 6 |

DOIs | |

State | Published - 4 Dec 2002 |