Secure exchange of information by synchronization of neural networks

Abstract

A connection between the theory of neural networks and cryptography is presented. A new phenomenon, namely synchronization of neural networks is leading to a new method of exchange of secret messages. Numerical simulations show that two artificial networks being trained by Hebbian learning rule on their mutual outputs develop an antiparallel state of their synaptic weights. The synchronized weights are used to construct an ephemeral key exchange protocol for a secure transmission of secret data. It is shown that an opponent who knows the protocol and all details of any transmission of the data has no chance to decrypt the secret message, since tracking the weights is a hard problem compared to synchronization. The complexity of the generation of the secure channel is linear with the size of the network.

11 pages, 5 figures

Cited by in corpus (23)

• Public channel cryptography by synchronization of neural networks and chaotic maps
• Genetic attack on neural cryptography
• Mutual learning in a tree parity machine and its application to cryptography
• Dynamics of neural cryptography
• A secure key-exchange protocol with an absence of injective functions
• Error correction in quantum cryptography based on artificial neural networks
• Cooperating Attackers in Neural Cryptography
• Public-channel cryptography using chaos synchronization
• Neural cryptography with feedback
• Do Small Worlds Synchronize Fastest?
• Cryptography based on neural networks - analytical results
• Entrainment of Coupled Oscillators on Regular Networks by Pacemakers
• Comment on novel public key encryption technique based on multiple chaotic systems
• Speed of complex network synchronization
• Neural cryptography with queries
• Reentrant Synchronization and Pattern Formation in Pacemaker-Entrained Kuramoto Oscillators
• Synchronization of random walks with reflecting boundaries
• Synchronization of Tree Parity Machines using non-binary input vectors
• Successful attack on permutation-parity-machine-based neural cryptography
• Chaos Synchronization with Dynamic Filters: Two Way is Better Than One Way
• Synchronization in a market model with time delays
• Seed-Induced Uniqueness in Transformer Models: Subspace Alignment Governs Subliminal Transfer
• Keys in the Weights: Transformer Authentication Using Model-Bound Latent Representations