Neural cryptography: Difference between revisions

Revision as of 18:38, 11 October 2019

Revision as of 19:05, 15 November 2019

Line 69:

:<math>\Theta(a,b)=0</math> if <math>a \ne b</math> otherwise <math>\Theta(a,b)=1</math>

And:

:<math>g(x)</math> is a [[Function_Function (mathematics)| function]] that keeps the <math>w_i</math> in the range <math>\{-L, -L+1,...,0,...,L-1,L\}</math>

=== Attacks and security of this protocol ===

Line 76:

==== Brute force ====

To provide a brute force attack, an attacker has to test all possible keys (all possible values of weights wij). By K hidden neurons, K*N input neurons and boundary of weights L, this gives (2L+1)^KN possibilities. For example, the configuration K = 3, L = 3 and N = 100 gives us 3*10²⁵³ key possibilities, making the attack impossible with today’stoday's computer power.

==== Learning with own tree parity machine ====

Line 127:

* [[Neural network|Neural Network]]

* [[Stochastic neural network]]

* [[Shor%27s's algorithm]]

== References ==