Genetic attack on neural cryptography.

@article{Ruttor2006GeneticAO,
  title={Genetic attack on neural cryptography.},
  author={Andreas Ruttor and Wolfgang Kinzel and Rivka Naeh and Ido Kanter},
  journal={Physical review. E, Statistical, nonlinear, and soft matter physics},
  year={2006},
  volume={73 3 Pt 2},
  pages={
          036121
        }
}
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… 
Neural synchronization and cryptography
TLDR
Neural networks can synchronize by learning from each other and can be used to construct a cryptographic key-exchange protocol, so that a passive attacker is usually unable to learn the generated key in time.
A New Security on Neural Cryptography with Queries
TLDR
The new parameter H can accomplish a higher level of security for the neural key-exchange protocol without altering the average synchronization time.
Analysis of Neural Synchronization Using Genetic Approach for Secure Key Generation
TLDR
The performance of the genetic algorithm has been analysed by varying the neural network and genetic parameters by generating the optimal weights for the sender and receiver from a genetic process.
Neural cryptography with queries for co-operating attackers and effective number of keys
TLDR
The increased synchronization time of the co-operating attacker against the flipping attack is also analyzed and the increased synchronization times of two Tree Parity Machines for agreement on a common secret key over a public channel are analyzed.
DISTRIBUTION OF THE TREE PARITY MACHINE SYNCHRONIZATION TIME
TLDR
Though the time needed to achieve compatible weights vectors in both partner networks depends on their topology, the histograms generated herein render similar distribution patterns and coincide with Poisson distribution, so there is no necessity of redoing again time-consuming computer simulations.
Neural synchronization based secret key exchange over public channels: A survey
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
Neural Cryptography Based on Complex-Valued Neural Network
TLDR
A neural cryptography based on the complex-valued tree parity machine network (CVTPM) is proposed, whose input, output, and weights are a complex value, which can be considered as an extension of TPM.
Neural cryptography using optimal structure of neural networks
TLDR
An overview of the optimal configuration of the neural network that enables the generation and establishment of a secret key between the two approved entities is suggested.
Appliance of Neuron Networks in Cryptographic Systems
TLDR
The study demonstrates neuro cryptographic protocol based on a three-level neural network of the direct propagation and analyzed three types of this algorithm attack to show the reality of the hypothesis that neuro cryptography is currently one of the most promising post quantum cryptographic systems.
Security analysis of neural cryptography implementation
TLDR
The information leakage through the learning process is investigated and it is shown how this information can be used to reduce the complexity of the genetic attack, a neural cryptography known attack strategy.
...
...

References

SHOWING 1-10 OF 20 REFERENCES
Advances in Cryptology — ASIACRYPT 2002
  • Yuliang Zheng
  • Computer Science
    Lecture Notes in Computer Science
  • 2002
TLDR
It is concluded that from a practical standpoint, the security of RSA relies exclusively on the hardness of the relation collection step of the number field sieve.
Statistical Mechanics of Learning
TLDR
The authors provide a coherent account of various important concepts and techniques that are currently only found scattered in papers, supplement this with background material in mathematics and physics, and include many examples and exercises.
Cryptography - theory and practice
  • D. Stinson
  • Computer Science, Mathematics
    Discrete mathematics and its applications series
  • 1995
Mech
  • 2005, P01009
  • 2005
Phys
  • Rev. E 66, 066102
  • 2002
Phys
  • Rev. E 69, 066137
  • 2004
A 36
  • 11173
  • 2003
A 33
  • L141
  • 2000
Phys
  • Rev. Lett. 91, 118701
  • 2003
Comput
  • 54, 421
  • 2005
...
...