Abstract:

Phishing, which involves tricking unsuspecting online users into revealing confidential information for fraudulent purposes, is the most commonly used social engineering and cyber attack. To avoid falling victim to these attacks, users should be aware of phishing websites and maintain a blacklist of known phishing websites. Early detection of phishing websites can be achieved through the use of machine learning and deep neural network algorithms. Among these methods, machine learning has proven to be the most effective in detecting phishing websites. However, despite these efforts, online users still fall prey to phishing websites, which mimic legitimate URLs and webpages. The objective of this project is to train machine learning models and deep neural networks on a dataset of phishing and benign website URLs to predict phishing websites. Relevant URL and website content-based features are extracted from the dataset to form a classification problem, where input URLs are classified as either phishing (1) or legitimate (0). The performance of each model, including Decision Tree, Random Forest, Multilayer Perceptrons, XGBoost, Autoencoder Neural Network, and Support Vector Machines, will be measured and compared.

Description:

Decision Tree, Random Forest, Multilayer Perceptrons, XGBoost, Autoencoder Neural Network, Support Vector Machines, Phishing attacks