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

Recurrent GANs Password Cracker For IoT Password Security Enhancement.

Sungyup Nam1, Seungho Jeon1, Hongkyo Kim1

  • 1Graduate School of Information Security, Korea University, Seoul 02841, Korea.

Sensors (Basel, Switzerland)
|June 4, 2020
PubMed
Summary

New methods improve password cracking performance by enhancing generative adversarial networks (GANs). These advanced techniques offer better password strength estimation, bolstering network security against common password vulnerabilities.

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

AutoKFL: Linux Kernel Fault Localization via ReAct-Based Multi-Agent Framework with Dynamic Crash Reproduction.

Sensors (Basel, Switzerland)·2026
Same author

Stack-based static WebAssembly binary slicing and mutation for generating valid sub-binaries.

Scientific reports·2026
Same author

Nanozyme Catalysis Restores Hair Follicle Integrity by Reversing Peroxisomal Collapse.

ACS nano·2026
Same author

Oxidative Stress-Responsive Chemo-Physical Deformation of Hydrogel with Pygo2 Knockdown for Prevention of Kidney Fibrosis.

Advanced healthcare materials·2026
Same author

FP-ZOO: Fast Patch-Based Zeroth Order Optimization for Black-Box Adversarial Attacks on Vision Models.

Sensors (Basel, Switzerland)·2025
Same author

Cloud edge enabled stacked ensemble learning framework with meta model for situation aware maritime traffic monitoring and control systems.

Scientific reports·2025

Area of Science:

  • Computer Science
  • Cybersecurity
  • Artificial Intelligence

Background:

  • Text-based passwords are a common authentication method but are vulnerable due to reliance on user memory, leading to weak, easily crackable passwords.
  • Internet of Things (IoT) devices often use default, weak passwords, creating significant network security risks.
  • Existing password cracking techniques like Markov models and Probabilistic Context-Free Grammar (PCFG) have limitations.

Purpose of the Study:

  • To improve the performance of password cracking using generative adversarial networks (GANs).
  • To develop advanced password cracking models that enhance password strength estimation.
  • To address the security vulnerabilities associated with weak and default passwords, particularly in IoT environments.

Main Methods:

Keywords:
GANIWGANIoTPCFGRNNhashcatpassGANpassword cracking

Related Experiment Videos

  • Modified the convolutional neural network (CNN)-based improved Wasserstein GAN (IWGAN) cost function to an RNN-based cost function.
  • Implemented a dual-discriminator GAN structure to enhance password cracking capabilities.
  • Compared the performance of the developed models against PassGAN and PCFG using password cracking experiments.

Main Results:

  • The developed models demonstrated a 10%-15% improvement in password cracking performance compared to PassGAN.
  • The models showed significant performance advantages over PCFG in cracking experiments.
  • The enhanced models proved effective in improving password strength estimation accuracy when compared with zxcvbn.

Conclusions:

  • The proposed RNN-based cost function and dual-discriminator GAN structure represent significant advancements in password cracking technology.
  • These improved models contribute to the development of more robust password strength checkers.
  • The research highlights a pathway to better securing networks by understanding and exploiting password weaknesses more effectively.