“Researchers from Bar Ilan University in Israel have combined chaos and neural networks in an effort to make a virtually unbreakable encryption code.

The difficult part of encryption is finding a truly random source to generate a key, and a way to give only the intended receiver the key.

One way to share a random source is to find some way to synchronize a pair of identical dynamic systems.

Chaotic systems and neural networks are good random sources because they are complicated. Chaotic systems can be synchronized using a common outside signal, and neural networks can become synchronized by affecting, or learning from, each other.

The researchers’ neural network encryption system includes a pair of software-based neural networks that can be synchronized by training each network on the others’ output signals, and a pair of chaotic maps. After a period of receiving identical signals the maps gradually become identical for a certain range of parameters even though they started out differently and their dynamics remain chaotic.”