Genetic attack on neural cryptography
Abstract
Different scaling properties for the complexity of bidirectional synchronization and unidirectional learning are essential for the security of neural cryptography. Incrementing the synaptic depth of the networks increases the synchronization time only polynomially, but the success of the geometric attack is reduced exponentially and it clearly fails in the limit of infinite synaptic depth. This method is improved by adding a genetic algorithm, which selects the fittest neural networks. The probability of a successful genetic attack is calculated for different model parameters using numerical simulations. The results show that scaling laws observed in the case of other attacks hold for the improved algorithm, too. The number of networks needed for an effective attack grows exponentially with increasing synaptic depth. In addition, finitesize effects caused by Hebbian and antiHebbian learning are analyzed. These learning rules converge to the random walk rule if the synaptic depth is small compared to the square root of the system size.
 Publication:

Physical Review E
 Pub Date:
 March 2006
 DOI:
 10.1103/PhysRevE.73.036121
 arXiv:
 arXiv:condmat/0512022
 Bibcode:
 2006PhRvE..73c6121R
 Keywords:

 84.35.+i;
 87.18.Sn;
 89.70.+c;
 Neural networks;
 Information theory and communication theory;
 Condensed Matter  Disordered Systems and Neural Networks
 EPrint:
 8 pages, 12 figures