DistilBERT reaches 99.78% accuracy on heterogeneous phishing datasets while CatBoost, CNN, and logistic regression also perform well; XAI methods identify key features and an MCP system enables real-time detection.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Explainable Machine Learning for Phishing Detection on Heterogeneous Datasets with MCP-Enabled Deployment
DistilBERT reaches 99.78% accuracy on heterogeneous phishing datasets while CatBoost, CNN, and logistic regression also perform well; XAI methods identify key features and an MCP system enables real-time detection.