Neural cryptography: Difference between revisions

Revision as of 22:48, 13 November 2016

Revision as of 01:13, 8 December 2016

Line 7:

The ideas of mutual learning, self learning, and stochastic behavior of neural networks and similar algorithms can be used for different aspects of cryptography, like [[public-key cryptography]], solving the [[Key (cryptography)|key]] distribution problem using neural network mutual synchronization, [[Cryptographic hash function|hashing]] or generation of [[Cryptographically secure pseudo-random number generator|pseudo-random numbers]].

Another idea is the ability of a neural network to separate space in non-linear pieces using "bias". It gives different probabilities of activating or not the neural network or not. This is very useful in the case of Cryptanalysis.

Two names are used to design the same ___domain of researches research: Neuro-Cryptography and Neural Cryptography.

The first work that it is known on this topic can be traced back to 1995 in an IT Master Thesis.