Search research articles

Search research articles

Related Experiment Videos

Explainable few-shot learning with modern BERT for detecting emerging phishing attacks using XF PhishBERT.

Mohammed Tawfik¹, Ashraf A Abu-Ein^2,3, Amr H Abdelhaliem⁴

¹Faculty of Computer and Information Technology, Sana'a University, Sana'a, Yemen. kmkhol01@gmail.com.

Scientific Reports

|December 1, 2025

Summary

Related Concept Videos

Understanding Deception

Understanding Deception

Deception is a pervasive aspect of human communication. Empirical studies have shown that most individuals engage in some form of deceit on a daily basis, with approximately 20% of social exchanges involving deceptive elements. Lying follows a developmental trajectory, peaking during adolescence and declining with age, possibly due to the maturation of cognitive control and social accountability.Cognitive and Social Factors in Deception DetectionDespite its prevalence, accurately detecting...

Stereotype Threat and Self-fulfilling Prophecies

Stereotype Threat and Self-fulfilling Prophecies

When we hold a stereotype about a person, we have expectations that he or she will fulfill that stereotype. A self-fulfilling prophecy is an expectation held by a person that alters his or her behavior in a way that tends to make it true. When we hold stereotypes about a person, we tend to treat the person according to our expectations. This treatment can influence the person to act according to our stereotypic expectations, thus confirming our stereotypic beliefs. Research by Rosenthal and...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

GreenAid: a confidence-weighted ensemble deep learning system for real-time plant disease detection and management.

Scientific reports·2026

Same author

KANWhisper: leveraging learnable activation functions for interpretable and efficient arabic automatic speech recognition.

Scientific reports·2026

Same author

MultiScaleKANNet: a hybrid CNN-KAN-transformer architecture for radiographic bone-loss risk stratification from knee X-rays.

Scientific reports·2026

Same author

FedEmoNet: Privacy-preserving federated learning with TCN-Transformer fusion for cross-corpus speech emotion recognition.

PloS one·2026

Same author

A privacy-preserving cloud storage framework with hybrid encryption, homomorphic keyword search, and blockchain-based integrity verification.

Scientific reports·2026

Same author

Few-shot android malware classification with quantum-enhanced prototypical learning and drift detection.

Scientific reports·2026

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

XF-PhishBERT offers explainable few-shot learning for phishing detection, achieving high accuracy with minimal data. This cybersecurity solution overcomes limitations of traditional methods by adapting to novel threats efficiently.

Area of Science:

Cybersecurity
Machine Learning
Artificial Intelligence

Background:

Phishing attacks evolve rapidly, outpacing traditional detection systems.
Machine learning models require extensive labeled data, creating vulnerabilities for new threats.
Acquiring labeled data for emerging cyber threats is costly and time-consuming.

Purpose of the Study:

To introduce XF-PhishBERT, an explainable few-shot learning framework for efficient phishing detection.
To enable effective phishing detection with minimal training examples.
To provide transparent decision-making support for security analysts.

Main Methods:

Combined ModernBERT transformer architecture with domain-specific URL features.
Integrated prototypical networks and model-agnostic meta-learning (MAML) for few-shot learning.

Keywords:

BERT Few-shot learning Large language models (LLMs)Meta-learning Phishing detection

Related Experiment Videos

Utilized consensus-based feature selection (Random Forest, Mutual Information, RFECV) and SHAP analysis for explainability.

Main Results:

Achieved 99.9% accuracy with 10 examples per class and 98.5% in one-shot learning.
Demonstrated 186% performance retention in cross-dataset evaluation, significantly outperforming traditional methods (39%).
Browser extension deployment showed 98.3% precision and 42ms latency.

Conclusions:

Few-shot learning effectively addresses the challenge of limited labeled data in cybersecurity.
XF-PhishBERT provides a robust and explainable solution for rapidly evolving phishing threats.
The framework enhances cybersecurity by enabling rapid adaptation and transparent threat analysis.