Unformatted text preview:

Slide 1Slide 2Slide 3Slide 4Slide 5Slide 6Slide 7Slide 8Slide 9Slide 10Slide 11Slide 12Slide 13Slide 14Slide 15Slide 16Neural CryptographyGroup A4Chris SunBryan MadenMin FangProblem of Symmetric KeyKey distributionKey distributionKey and securityThe more we use a same keythe more easily to beak the codeOne-time padUnbreakableUnbreakableCipherKey 1Key 1Plain 1Key 2Key 2Plain 2Key 3Key 3Plain 3Plain XKey XKey XProblem of key distributionNo secure channelContact in personToo expensiveNN to implement one-time padIf this is true we have a perfect codeIf this is true we have a perfect codeBasic NNInputsampleHiddenlayerOutputPropagation ruleWeightActivation functionTrainingInputsampleHiddenlayerOutputcompareModify weightsNN 1Public random bit streamNN 2Output 1Output 2NN CryptographyAll input and output are known to the public.All weights are unknown to the public, even the partner.NN Cryptography -2Each NN trains by the output from his partner.After synchronization, the final weights is the key.Example of NN used in cryptographyQuestion?The


View Full Document
Download Neural Cryptography
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Neural Cryptography and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Neural Cryptography 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?