ITDS | SPMS

Detecting E-Banking Phishing Using Associative Classification

Project Description
Supervisor

Particularly for online banking and e-commerce systems, where it regularly leads to significant financial losses and undermines consumer confidence in digital infrastructure, phishing is still a significant and developing cybersecurity threat. Blacklists and heuristic-based filtering are two examples of traditional mitigation techniques that have demonstrated poor efficacy, particularly when it comes to identifying new or dynamically produced phishing sites. This study addresses these shortcomings by presenting a complex phishing detection framework that makes use of associative classification, a cutting-edge hybrid machine learning technique that combines classification algorithms and association rule mining to improve detection effectiveness. To correctly categorize online pages as benign or malicious, the suggested model makes use of discriminative information extracted from website metadata, such as URL syntax, domain registration duration, and SSL certificate usage. A carefully selected dataset with annotated instances of both authentic and phishing URLs will be used to train and validate the system. According to initial projections, this method will outperform conventional detection methods, especially when it comes to measures like accuracy, precision, and recall. In order to improve defenses against phishing assaults in increasingly digitalized financial ecosystems, this study promotes a scalable, data-centric paradigm.

Machine Learning: Machine Learning (ML) research in Computer Science and Information Technology focuses on the development of algorithms and models that enable computers to learn from data and improve their performance over time without being explicitly programmed. It is a subset of Artificial Intelligence that uses statistical techniques to give machines the ability to learn patterns, make decisions, and predict outcomes based on data. Supervised learning, a key area of ML research, involves training models on labeled data, where the input-output relationships are predefined. This method is widely used for tasks such as classification (e.g., spam detection) and regression (e.g., predicting house prices). Unsupervised learning, on the other hand, involves finding hidden patterns in data without predefined labels, with clustering and association being typical applications in areas such as customer segmentation and anomaly detection. Reinforcement learning is another area of ML that focuses on teaching agents to make decisions by interacting with their environment and receiving feedback in the form of rewards or penalties. It is often applied in robotics, game playing, and autonomous systems, where continuous learning and adaptation are required.