Applicability of Machine Learning in Spam and Phishing Email Filtering: Review and Approaches

Metadane

• Autorzy: T. Gangavarapu, C.D. Jaidhar, B. Chanduka
• Rok: 2020
• Źródło: Artificial Intelligence Review, Volume 53, Pages 5019–5081
• DOI/Link: 10.1007/S10462-020-09814-9
• Status: to-read
• Pochodzenie: Wyekstrahowane z al-subaiey-web-ai-phishing-2024 ([18] - review + Random Forest 98.4% accuracy)
• Tagi: to-read reference spam-filtering phishing machine-learning review-paper random-forest

Notatki

Publikacja dodana automatycznie z bibliografii.

Kontekst cytowania w Al-Subaiey 2024:

• Referenced jako [18] w paper (cited multiple times)
• Review of ML approaches for spam AND phishing
• Proposed Random Forest with feature selection: 98.4% accuracy (ham-spam), 99.4% (ham-phishing)
• Dataset: SpamAssassin + Nazario (3,051 2-class, 3,344 2-class, 3,844 3-class)
• Future work mentioned: improving robustness, exploring graphical features
• Informed Al-Subaiey’s model selection i comparison benchmarks

Key Finding (cited):

• Content and behavior-based features effective
• Random Forest strong baseline performance

Dodaj PDF aby wygenerować pełne podsumowanie używając /summarize-paper gangavarapu-spam-phishing-filtering-review-2020