Home // SECURWARE 2025, The Nineteenth International Conference on Emerging Security Information, Systems and Technologies // View article

A Comparative Study of Machine Learning and Quantum Models for Spam Email Detection

Authors:
Cameron Williams
Taieba Tasnim
Berkeley Wu
Mohammad Rahman
Fan Wu

Keywords: KNN; FNN; CNN; SVM; QCNN; Machine Learning; Deep Learning; Quantum Computing.

Abstract:
This research focused on evaluating the performance of seven different machine learning algorithms including Naive Bayes, K-Nearest Neighbors (KNN), Logistic Regression, Support Vector Machine (SVM), Feedforward Neural Network (FNN), Convolutional Neural Network (CNN), and Quantum Convolutional Neural Network (QCNN) using a single labeled email dataset. Each algorithm was applied to the same set of data and tested for its ability to detect spam and classify various types of abnormal behavior patterns. The study aimed to benchmark the accuracy of each model in a consistent environment to understand how well they handled real-world classification challenges. After processing and training the models, their outputs were compared based on accuracy, with results compiled into a bar chart for clear comparison. The findings highlight the strengths and limitations of each approach, providing insight into which models are better suited for tasks, such as spam detection, anomaly detection, and pattern recognition in email-based data.

Pages: 147 to 152

Copyright: Copyright (c) IARIA, 2025

Publication date: October 26, 2025

Published in: conference

ISSN: 2162-2116

ISBN: 978-1-68558-306-4

Location: Barcelona, Spain

Dates: from October 26, 2025 to October 30, 2025