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

Cooperating attackers in neural cryptography.

Lanir N Shacham1, Einat Klein, Rachel Mislovaty

  • 1Minerva Center and Department of Physics, Bar-Ilan University, Ramat-Gan 52900, Israel.

Physical Review. E, Statistical, Nonlinear, and Soft Matter Physics
|July 13, 2004
PubMed
Summary

A novel majority-flipping attacker successfully compromises neural cryptography systems. This cooperative attack strategy exploits mutual learning synchronization, outperforming previous methods and remaining effective regardless of system parameters.

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

Area of Science:

  • Cryptography
  • Artificial Intelligence
  • Network Security

Background:

  • Neural cryptosystems utilize mutual learning for secure synchronization.
  • Previous research indicated robustness against various attack strategies.
  • The security of these systems is crucial for modern data protection.

Purpose of the Study:

  • To present a new, highly effective attack strategy against neural cryptosystems.
  • To analyze the mechanism and effectiveness of the proposed attack.
  • To demonstrate the vulnerability of neural cryptosystems to cooperative attacks.

Main Methods:

  • Introduction of the 'majority-flipping attacker' concept.
  • Simulation of the attack strategy within a neural cryptosystem.

Related Experiment Videos

  • Analytical modeling of the attacker's cooperative behavior during synchronization.

    • Main Results:

    • The majority-flipping attacker achieves significant success rates.
    • Attack effectiveness remains consistent across varying model parameters.
    • Cooperative action among attackers is key to the strategy's success.

    Conclusions:

    • Neural cryptosystems are vulnerable to sophisticated, cooperative attack strategies.
    • The majority-flipping attacker represents a significant advancement in cryptanalysis.
    • Further research is needed to develop defenses against such cooperative attacks.