Developing a Google Chrome Extension for Detecting Phishing Emails

Hongkai Chen, Dr. Mohammad Hossain, and Dr. Sameer Abufardeh, Department of Math, Science and Technology, University of Minnesota Crookston, 2900 University Ave, Crookston MN 56716

Phishing is a fraudulent attempt where phishers trick the victims into disclosing sensitive information under pretenses. This research project aims to develop a Google Chrome extension to detect phishing emails using a model or algorithm. To develop an effective Google Chrome extension for anti-phishing, the most important part is to explore an accurate and reasonable algorithm or model. Previous studies have investigated different methods and algorithms. Ayodele et al. (2012) propose a machine learning framework MLAPT to detect phishing emails. This system is able to judge the domains of the websites and detect the security of the websites by detecting the similarity. Meanwhile, according to Fang et al. (2019), a new phishing email detection model named THEMIS is based on an improved recurrent convolutional neural networks (RCNN) model with multilevel vectors and attention mechanisms. Among these published algorithms and models, we will find one that can be used for our Google Chrome extension. With a robust algorithm or model, we can think of the email text as an input and throw it into the model. Then there will be an output that tells us whether the email is a phishing email or not. To find out the best model or algorithm, we collected a sufficient amount of models and algorithms from publications. Our next step will be to test them with phishing email samples and standard email samples. After that, the accuracy and the false positive rate (FPR) will be collected to determine which algorithm is the best. Once the best algorithm is determined, we will use it to develop a Google Chrome extension. Then the extension will be tested by volunteers. After debugging and improvement, we will launch the extension and make it accessible to all students, faculty, and staff within the university system.

Additional Abstract Information

Presenter: Hongkai Chen

Institution: University of Minnesota - Crookston

Type: Oral

Subject: Computer Science

Status: Approved

Time and Location

Session: Oral 7
Date/Time: Tue 3:30pm-4:30pm
Session Number: 714
List other presenters in this same room and session