individual
What campus are you from?
Daytona Beach
Authors' Class Standing
Justin Villa, Senior
Lead Presenter's Name
Justin Villa
Faculty Mentor Name
Laxima Niure Kandel
Abstract
Phishing attacks have evolved into a sophisticated cybersecurity threat, targeting individuals and organizations through emails, websites and social media platforms. Current detection methods rely on predefined rules and deep learning models, but they struggle to identify new and evolving phishing techniques. This research proposes an adaptive hybrid AI approach that integrates Random Forest (RF) and Long Short-Term Memory (LSTM) neural networks. RF is effective for analyzing structured phishing data, while LSTM can detect patterns in sequential data, such as phishing messages. To improve accuracy and adaptability, we will incorporate adversarial training and explainable AI techniques. A key contribution of this research is the creation of a continuously updated phishing dataset, which integrates website URLs and social media phishing messages. By addressing the limitations of static datasets, our model will be better equipped to detect new phishing threats in real time. This project aims to enhance phishing detection capabilities, improve AI transparency, and provide a practical security solution for online users.
Did this research project receive funding support from the Office of Undergraduate Research.
No
Harnessing Hybrid-AI for Real-Time Phishing Detection
Phishing attacks have evolved into a sophisticated cybersecurity threat, targeting individuals and organizations through emails, websites and social media platforms. Current detection methods rely on predefined rules and deep learning models, but they struggle to identify new and evolving phishing techniques. This research proposes an adaptive hybrid AI approach that integrates Random Forest (RF) and Long Short-Term Memory (LSTM) neural networks. RF is effective for analyzing structured phishing data, while LSTM can detect patterns in sequential data, such as phishing messages. To improve accuracy and adaptability, we will incorporate adversarial training and explainable AI techniques. A key contribution of this research is the creation of a continuously updated phishing dataset, which integrates website URLs and social media phishing messages. By addressing the limitations of static datasets, our model will be better equipped to detect new phishing threats in real time. This project aims to enhance phishing detection capabilities, improve AI transparency, and provide a practical security solution for online users.