Towards Text-based Phishing Detection

TL;DR

This study improves text-based phishing detection accuracy using a modified algorithm with readily available resources, highlighting potential for further reduction in false positives with semantic analysis.

Contribution

It presents a modified phishing detection algorithm that outperforms previous non-semantic methods in accuracy, using accessible tools.

Findings

Better phishing email recognition accuracy

Slightly higher false positive rate

Potential for semantic analysis to improve results

Abstract

This paper reports on an experiment into text-based phishing detection using readily available resources and without the use of semantics. The developed algorithm is a modified version of previously published work that works with the same tools. The results obtained in recognizing phishing emails are considerably better than the previously reported work; but the rate of text falsely identified as phishing is slightly worse. It is expected that adding semantic component will reduce the false positive rate while preserving the detection accuracy.