Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Dynamics of neural cryptography.

Andreas Ruttor1, Wolfgang Kinzel, Ido Kanter

  • 1Institut für Theoretische Physik, Universität Würzburg, Am Hubland, 97074 Würzburg, Germany.

Physical Review. E, Statistical, Nonlinear, and Soft Matter Physics
|August 7, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Advanced deep architecture pruning using single-filter performance.

Physical review. E·2025
Same author

Towards a universal mechanism for successful deep learning.

Scientific reports·2024
Same author

Hebbian dreaming for small datasets.

Neural networks : the official journal of the International Neural Network Society·2024
Same author

Enhancing the accuracies by performing pooling decisions adjacent to the output layer.

Scientific reports·2023
Same author

Efficient shallow learning as an alternative to deep learning.

Scientific reports·2023
Same author

Learning on tree architectures outperforms a convolutional feedforward network.

Scientific reports·2023
Same journal

Tension on dsDNA bound to ssDNA-RecA filaments may play an important role in driving efficient and accurate homology recognition and strand exchange.

Physical review. E, Statistical, nonlinear, and soft matter physics·2016
Same journal

Publisher's Note: Amplitude-phase coupling drives chimera states in globally coupled laser networks [Phys. Rev. E 91, 040901(R) (2015)].

Physical review. E, Statistical, nonlinear, and soft matter physics·2016
Same journal

Erratum: Shapes of sedimenting soft elastic capsules in a viscous fluid [Phys. Rev. E 92, 033003 (2015)].

Physical review. E, Statistical, nonlinear, and soft matter physics·2016
Same journal

Erratum: Attenuation of excitation decay rate due to collective effect [Phys. Rev. E 90, 022142 (2014)].

Physical review. E, Statistical, nonlinear, and soft matter physics·2016
Same journal

Publisher's Note: Role of connectivity and fluctuations in the nucleation of calcium waves in cardiac cells [Phys. Rev. E 92, 052715 (2015)].

Physical review. E, Statistical, nonlinear, and soft matter physics·2016
Same journal

Publisher's Note: Lattice Boltzmann approach for complex nonequilibrium flows [Phys. Rev. E 92, 043308 (2015)].

Physical review. E, Statistical, nonlinear, and soft matter physics·2016
See all related articles

Neural networks synchronize faster than they learn, a key security feature for neural key-exchange protocols. However, larger networks lose this advantage, limiting their use in neural cryptography.

Area of Science:

  • Computational neuroscience
  • Cryptography
  • Machine learning

Background:

  • Neural networks, specifically tree parity machines, are explored for cryptographic applications.
  • Synchronization dynamics in these networks are influenced by stochastic forces, modeled as random walks.

Purpose of the Study:

  • To analyze the synchronization and learning dynamics of tree parity machines for cryptographic protocols.
  • To determine the suitability of these networks for secure neural cryptography.

Main Methods:

  • Analytical derivation of transition probabilities and scaling laws for random walk models of neural network overlap.
  • Numerical simulations to validate analytical findings on synchronization and learning dynamics.
  • Calculation of the effective number of keys using the entropy of the weight distribution.

Related Experiment Videos

Main Results:

  • Bidirectional interaction in tree parity machines leads to faster, full synchronization compared to unidirectional learning.
  • Learning in these networks relies on fluctuations, making synchronization significantly quicker, which is crucial for security.
  • The advantage of faster synchronization diminishes in networks with more than three hidden units.

Conclusions:

  • Tree parity machines with fewer than four hidden units are suitable for neural cryptography due to distinct synchronization and learning speeds.
  • The exponential increase in key generation capacity with system size makes neural cryptography resistant to brute-force attacks.