Neural Synchronization based Secret Key Exchange over Public Channels: A survey
Preprint
Abstract
Exchange of secret keys over public channels based on neural synchronization using a variety of learning rules offer an appealing alternative to number theory based cryptography algorithms. Though several forms of attacks are possible on this neural protocol e.g. geometric, genetic and majority attacks, our survey finds that deterministic algorithms that synchronize with the end-point networks have high time complexity, while probabilistic and population-based algorithms have demonstrated ability to decode the key during its exchange over the public channels. Our survey also discusses queries, heuristics, erroneous information, group key exchange, synaptic depths, etc, that have been proposed to increase the time complexity of algorithmic interception or decoding of the key during exchange. The Tree Parity Machine and its variants, neural networks with tree topologies incorporating parity checking of state bits, appear to be one of the most secure and stable models of the end-point networks. Our survey also mentions some noteworthy studies on neural networks applied to other necessary aspects of cryptography. We conclude that discovery of neural architectures with very high synchronization speed, and designing the encoding and entropy of the information exchanged during mutual learning, and design of extremely sensitive chaotic maps for transformation of synchronized states of the networks to chaotic encryption keys, are the primary issues in this field.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Parallel hash function construction based on coupled map latticesCommunications in Nonlinear Science and Numerical Simulation, 2011
- Parallel keyed hash function construction based on chaotic neural networkNeurocomputing, 2009
- Permutation parity machines for neural synchronizationJournal of Physics A: Mathematical and Theoretical, 2009
- Adaptive synchronization and lag synchronization of uncertain dynamical system with time delay based on parameter identificationPhysica A: Statistical Mechanics and its Applications, 2007
- Cryptography based on delayed chaotic neural networksPhysics Letters A, 2006
- Genetic attack on neural cryptographyPhysical Review E, 2006
- Neural cryptography with queriesJournal of Statistical Mechanics: Theory and Experiment, 2005
- Cooperating attackers in neural cryptographyPhysical Review E, 2004
- Mutual learning in a tree parity machine and its application to cryptographyPhysical Review E, 2002
- Equivalence between learning in noisy perceptrons and tree committee machinesPhysical Review E, 1996