Using Echo State Networks for Cryptography
This addresses secure data transmission for users needing encryption, but it is incremental as it applies an existing neural network type to cryptography.
The paper tackled secure communication by proposing a neural cryptography scheme using echo state networks, where Alice and Bob share a network to encrypt and decrypt messages, and experiments showed it satisfies cryptographic properties like diffusion and confusion.
Echo state networks are simple recurrent neural networks that are easy to implement and train. Despite their simplicity, they show a form of memory and can predict or regenerate sequences of data. We make use of this property to realize a novel neural cryptography scheme. The key idea is to assume that Alice and Bob share a copy of an echo state network. If Alice trains her copy to memorize a message, she can communicate the trained part of the network to Bob who plugs it into his copy to regenerate the message. Considering a byte-level representation of in- and output, the technique applies to arbitrary types of data (texts, images, audio files, etc.) and practical experiments reveal it to satisfy the fundamental cryptographic properties of diffusion and confusion.