Title: Detection of Phishing Emails with Email Forensic Analysis and Machine Learning Techniques

Issue Number: Vol. 8, No. 2
Year of Publication: Jun - 2019
Page Numbers: 98-107
Authors: Kamran Morovati, Sanjay S.Kadam
Journal Name: International Journal of Cyber-Security and Digital Forensics (IJCSDF)
- Hong Kong
DOI:  http://dx.doi.org/10.17781/P002568


This research is an attempt to investigate the effectiveness of email forensic analysis and text mining techniques in identifying phishing emails. The dataset that is used for this experiment consist of suspicious emails reported by our clients that were delivered in their inboxes and hence our anti-spam solution was not able to detect them. In this paper, the importance of inspecting the email header fields and their role in verifying the legitimacy of an email address is discussed. Moreover, use of techniques such as readability metrics and text mining methods such as frequent pattern detection, association rules and document similarity for phish detection are explained. Lastly, a few binary email classifiers are trained and tested and their results are interpreted.