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

Genetic attack on neural cryptography.

Andreas Ruttor1, Wolfgang Kinzel, Rivka Naeh

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

Physical Review. E, Statistical, Nonlinear, and Soft Matter Physics
|April 12, 2006
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

Increasing synaptic depth in neural networks enhances security by exponentially reducing geometric attack success. Genetic algorithms further improve this defense, requiring exponentially more networks for effective attacks as depth increases.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Cryptography

Background:

  • Neural cryptography security relies on distinct scaling properties of synchronization and learning.
  • Geometric attacks pose a threat to neural network security.

Purpose of the Study:

  • To analyze the impact of synaptic depth on neural network security against geometric attacks.
  • To evaluate an improved attack method incorporating a genetic algorithm.

Main Methods:

  • Numerical simulations to calculate the probability of successful genetic attacks.
  • Analysis of scaling laws and finite-size effects for different learning rules.

Main Results:

  • Increasing synaptic depth polynomially increases synchronization time but exponentially decreases geometric attack success.

Related Experiment Videos

  • The genetic algorithm improves attack efficacy, with success probability following established scaling laws.
  • Attack complexity grows exponentially with synaptic depth.

    • Conclusions:

    • Enhanced synaptic depth is crucial for robust neural cryptography.
    • Genetic algorithms offer a scalable approach to analyzing and potentially overcoming neural network defenses.