Business Email Compromise Phishing Detection Based on Machine Learning: A Systematic Literature Review

Metadane

• Autorzy: H.F. Atlam, O. Oluwatimilehin
• Rok: 2022
• Źródło: Electronics (Basel), Volume 12, Issue 1, Page 42
• DOI/Link: 10.3390/electronics12010042
• Status: to-read
• Pochodzenie: Wyekstrahowane z al-subaiey-web-ai-phishing-2024 ([20] - BEC-specific review, XAI integration recommendation)
• Tagi: to-read reference bec-phishing business-email-compromise machine-learning systematic-review explainable-ai

Notatki

Publikacja dodana automatycznie z bibliografii.

Kontekst cytowania w Al-Subaiey 2024:

• Referenced jako [20] w paper
• Systematic review of BEC (Business Email Compromise) phishing attacks (2012-2022)
• Key Findings (from Al-Subaiey citation):
  1. ML promising for detecting evolving BEC attacks (Decision Tree, SVM, Neural Networks common)
  2. Email body AND header features crucial
  3. Future research directions:
     • Dynamic feature selection
     • Realistic datasets
     • Integrating NLP with deep learning
     • Combining ML with Explainable AI (XAI) ← directly influenced Al-Subaiey’s LIME integration

Significance for Al-Subaiey 2024:

• Motivated XAI integration (LIME) for interpretability
• Informed feature selection (body + header)
• Highlighted gap in realistic datasets → Al-Subaiey addressed with comprehensive 82k dataset

Dodaj PDF aby wygenerować pełne podsumowanie używając /summarize-paper atlam-bec-phishing-ml-review-2022