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 Video

Updated: Dec 26, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.3K

CAPTCHA Image Generation: Two-Step Style-Transfer Learning in Deep Neural Networks.

Hyun Kwon1, Hyunsoo Yoon2, Ki-Woong Park3

  • 1Department of Electrical Engineering, Korea Military Academy, Seoul 01805, Korea.

Sensors (Basel, Switzerland)
|March 19, 2020
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

LUMEN: A Lightweight UAV Multi-Enhanced Network for PSD-Based RF Fingerprinting on Edge Devices.

Sensors (Basel, Switzerland)·2026
Same author

Integrating vibration signal analysis and image embedding for enhanced bearing fault diagnosis in manufacturing.

Scientific reports·2025
Same author

Healthy core: Harmonizing brain MRI for supporting multicenter migraine classification studies.

PloS one·2024
Same author

Multiclass classification of Alzheimer's disease prodromal stages using sequential feature embeddings and regularized multikernel support vector machine.

NeuroImage·2024
Same author

Biologically informed deep neural networks provide quantitative assessment of intratumoral heterogeneity in post treatment glioblastoma.

NPJ digital medicine·2024
Same author

OOSP: Opportunistic Optimization Scheme for Pod Deployment Enhanced with Multilayered Sensing.

Sensors (Basel, Switzerland)·2024
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles

This study introduces a novel method for creating CAPTCHA images resistant to automated attacks. By using style transfer, these images remain recognizable to humans while significantly reducing machine recognition rates.

Area of Science:

  • Computer Science
  • Cybersecurity
  • Artificial Intelligence

Background:

  • Web services face automated attacks, necessitating security measures like CAPTCHAs.
  • Highly distorted CAPTCHAs, while secure, are difficult for humans to decipher.

Purpose of the Study:

  • To develop a CAPTCHA generation method that resists machine recognition but remains human-recognizable.
  • To enhance CAPTCHA security without compromising user experience.

Main Methods:

  • Utilized style transfer to create 'style-plugged-CAPTCHA' images.
  • Incorporated external image styles into original CAPTCHA content.
  • Employed TensorFlow and six real-world CAPTCHA datasets for experimentation.

Main Results:

Keywords:
CAPTCHAconvolutional neural network (CNN)image style transfermachine learningneural network

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

936

Related Experiment Videos

Last Updated: Dec 26, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.3K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

936
  • Reduced DeCAPTCHA system recognition rates to 3.5% (one style image) and 3.2% (two style images).
  • Maintained human recognizability of the generated CAPTCHA images.

Conclusions:

  • The proposed style transfer method effectively balances CAPTCHA security and human usability.
  • This approach offers a promising solution to automated attacks on web services.