Abstract:
Web page phishing is a type of phishing attack that targets websites. In a web page phishing attack, the attacker creates a fake website that looks like a legitimate website, such as a bank or credit card company website. The attacker then sends a fraudulent message to the victim, which contains a link to the fake website. When the victim clicks on the link, they are taken to the fake website and tricked into entering their personal information.Web page phishing attacks are a serious threat to online security. They can be very effective, as they often look very convincing. To protect yourself from web page phishing attacks, you should be suspicious of any emails or messages that ask for your personal information. Do not click on links in emails or messages from unknown senders. If you are unsure whether a website is legitimate, do not enter your personal information.Therefore, in this study, we present a novel approach to detect whether a web page is phishing or legitimate using a neural network model. Our dataset was collected from Kaggle, includes 11481 URLs with 87 extracted features. The dataset is designed to be used as benchmarks for machine learning-based phishing detection systems. Features are from three different classes: 56 extracted from the structure and syntax of URLs, 24 extracted from the content of their correspondent pages, and 7 are extracted by querying external services. The dataset is balanced, it contains exactly 50% phishing and 50% legitimate URLs. The proposed model, consisting of two layers (1 input, 1 output),where the criterion was to minimize the error function in neural network training using a neural network model. After training the ANN model, the average error function of the neural network was equal to 0.041455 and the accuracy of the detection of whether a web page is phishing or not was 94.31% .
|