Open Access Open Access  Restricted Access Subscription Access

AI BASED E-MAIL AND DOMAIN SPOOFING DETECTION

Anitha. S, Muthukumaran. M, Paramesh. R, Sanjay Kumar. S, Sheik Musthafa. M

Abstract


In digital day to day life email is one of the most used communication system, but it is also a common entry point for cyberattacks. Email spoofing is one of the most threats to an indivisual or a group, where attackers pretend their emails to make them look like they’re coming from some trusted resources. To overcome this issue, we built an email spoofing detection system that combine machine learning with authentication on mails. TF-IDF is used to show meaningful patterns from the email content and a Random Forest algorithm to classify whether an email is spoofed or not. On top of that, it checks if the sender’s domain is verified using SPF and DMARC records. Emails are accessed securely using the Gmail API and OAuth 2.0, and the results are shown to the user through a simple web interface built with Flask. This analyses both content and origin of mails, thus helps users avoid spoofed messages more accurately and also in real time.


Full Text:

PDF

References


Shukla, S., Misra, M., & Varshney, G. (2023). Spoofed Email Based Cyberattack Detection Using Machine Learning. Journal of Computer Information Systems.

Beaman, C., & Isah, H. (2022). Anomaly Detection in Emails using Machine Learning and Header Information. arXiv:2203.10408.

Coalition Inc. (n.d.). Authenticating Email Using SPF, DKIM & DMARC.

Kambourakis, G., et al. (2023). SPF, DKIM, and DMARC adoption: The good, the bad, and the ugly. Computers & Security.

Google Developers. (n.d.). Using OAuth 2.0 for Web Server Applications.

Charanarur, P., et al. (2023). Machine-Learning-Based Spam Mail Detector. SN Computer Science, 4, 858.

Nayak, R., Jiwani, A., & Rajitha, B. (2021). Spam email detection using machine learning algorithm. Materials Today: Proceedings, 4(11), 862.

Ahmed, M., et al. (2022). Machine Learning Techniques for Spam Detection in Email and IoT Platforms: Analysis and Research Challenges. Security and Communication Networks, 2022.

Saeed, F., & Aghbari, Z. (2023). Survey on Deep Learning Approaches for Detection of Email Security Threat. Computers, Materials & Continua, 77(1), 325–348.

Jáñez-Martino, F., et al. (2023). A review of spam email detection: analysis of spammer strategies and the dataset shift problem. Artificial Intelligence Review, 56, 1145–1173.


Refbacks

  • There are currently no refbacks.