Neural cryptography with feedback

Andreas Ruttor, Wolfgang Kinzel, Lanir Shacham, Ido Kanter

Research output: Contribution to journalArticlepeer-review

34 Scopus citations

Abstract

The various aspects of neural cryptography with feedback are discussed. Neural cryptography is based on a competition between attractive and repulsive stochastic forces. It is noted that when a system of interacting neurons adjusts its couplings to a set of externally produced examples, this network is able to estimate the rule which produced the examples. It is observed that a network with feedback generates a pseudorandom bit sequence which can be used to encrypt and decrypt a secret message.

Original languageEnglish
Article number046110
Pages (from-to)046110-1-046110-7
JournalPhysical Review E
Volume69
Issue number4 2
StatePublished - Apr 2004

Fingerprint

Dive into the research topics of 'Neural cryptography with feedback'. Together they form a unique fingerprint.

Cite this