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: Apr 4, 2026

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

2.8K

Deep learning-based phishing classification framework for accurate detection using optimized URL intelligence.

R Gobinath1, S Manikandan2

  • 1Department of Artificial Intelligence and Data Science, E.G.S. Pillay Engineering College, Nagapattinam, Tamil Nadu, India. gobinath@egspec.org.

Scientific Reports
|April 2, 2026
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

Estimation of heterosis and combining ability under low soil phosphorus condition in rice (Oryza sativa L.).

Scientific reports·2025
Same author

Disparities in Brain Death Certification Knowledge among Indian Physicians Involved in Organ Donation.

Neurology India·2025
Same author

Design, fabrication, and<i>in vitro</i>evaluation of a 3D printed, bio-absorbable PLA tibia bone implant with a novel lattice structure.

Biomedical physics & engineering express·2025
Same author

Prescribing trends of fixed-dose combination of domperidone and proton-pump inhibitor across tertiary care centers in India, is the combination rational?

Indian journal of pharmacology·2025
Same author

3D bio-printed scaffolds and smart implants: evaluating functional performance in animal surgery models.

Annals of medicine and surgery (2012)·2025
Same author

Retraction notice to "Advances in bioremediation of emerging contaminants from industrial wastewater by oxidoreductase enzymes" [Bioresour. Technol. 359 (2022) 127444].

Bioresource technology·2025

This study introduces the Adaptive Deep URL Intelligence Network (ADUIN) to combat evolving phishing URL threats. ADUIN enhances phishing detection accuracy and adaptability, significantly reducing false positives and improving zero-day URL identification.

Area of Science:

  • Cybersecurity
  • Machine Learning
  • Network Security

Background:

  • Phishing attacks exploit internet service proliferation using deceptive URLs.
  • Existing detection methods struggle with dynamic, zero-day, and camouflaged phishing URLs due to reliance on static features or blacklists.
  • High false-positive rates and poor scalability limit current phishing detection system performance.

Purpose of the Study:

  • To propose an Adaptive Deep URL Intelligence Network (ADUIN) for intelligent phishing URL detection.
  • To develop a system that overcomes the limitations of traditional rule-based and signature-based detection methods.
  • To enhance the accuracy, adaptability, and scalability of phishing URL classification.

Main Methods:

  • Developed ADUIN, a deep learning model integrating optimized URL lexical, host-based, and structural features.
Keywords:
CybersecurityDeep LearningFeature OptimizationPhishing DetectionURL IntelligenceWebsite Classification

Related Experiment Videos

Last Updated: Apr 4, 2026

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

2.8K
  • Employed a hybrid relevance-ranking method for feature optimization.
  • Trained a multi-layer deep neural architecture capable of understanding complex, non-linear phishing patterns.
  • Implemented dynamic architecture updates for URL intelligence to adapt to changing attack behaviors.

    • Main Results:

    • ADUIN demonstrated superior accuracy, precision, and recall compared to existing machine learning classifiers on benchmark datasets.
    • Achieved 95% classification accuracy, 93% precision, and a 92% zero-day detection rate with only 3.5% false positives under high load.
    • Optimal accuracy was achieved with 50 features, showing efficient feature utilization.
    • The system exhibited a low delay of 210 ms, suitable for real-time applications.

    Conclusions:

    • ADUIN significantly improves phishing URL classification accuracy, versatility, and intelligence.
    • The proposed system effectively detects zero-day phishing URLs with minimal false alarms.
    • ADUIN offers a robust solution for real-time online and enterprise security, enhancing defenses against sophisticated phishing techniques.