Phishing Detection System Through Hybrid Machine Learning Based on URL

Abstract

Currently, numerous types of cybercrime are organized through the internet. Hence, this study mainly focuses on phishing attacks. Although phishing was first used in 1996, it has become the most severe and dangerous cybercrime on the internet. Phishing utilizes email distortion as its underlying mechanism for tricky correspondences, followed by mock sites, to obtain the required data from people in question. Different studies have presented their work on the precaution, identification, and knowledge of phishing attacks; however, there is currently no complete and proper solution for frustrating them. Therefore, machine learning plays a vital role in defending against cybercrimes involving phishing attacks. The proposed study is based on the phishing URL-based dataset extracted from the famous dataset repository, which consists of phishing and legitimate URL attributes collected from 11000+ website datasets in vector form. After preprocessing, many machine learning algorithms have been applied and designed to prevent phishing URLs and provide protection to the user. This study uses machine learning models such as decision tree (DT), linear regression (LR), random forest (RF), naive Bayes (NB), gradient boosting classifier (GBM), K-neighbors classifier (KNN), support vector classifier (SVC), and proposed hybrid LSD model, which is a combination of logistic regression, support vector machine, and decision tree (LR+SVC+DT) with soft and hard voting, to defend against phishing attacks with high accuracy and efficiency. The canopy feature selection technique with cross fold valoidation and Grid Search Hyperparameter Optimization techniques are used with proposed LSD model. Furthermore, to evaluate the proposed approach, different evaluation parameters were adopted, such as the precision, accuracy, recall, F1-score, and specificity, to illustrate the effects and efficiency of the models. The results of the comparative analyses demonstrate that the proposed approach outperforms the other models and achieves the best results.

Web Attack Intrusion Detection System Using Machine Learning Techniques

“…The k-nearest neighbors (KNN) algorithm is considered one of the most fundamental classification techniques in machine learning, specifically in supervised learning [28,29]. Using KNN can yield a respectable level of accuracy in making predictions through classification [28].…”

“…The KNN algorithm heavily relies on the value of k to determine the number of neighbors that should be selected based on the input data, as shown in Figure 2 [30]. The KNN algorithm is simple and easy to understand and execute [28,29]. However, as the amount of data being used increases, finding the ideal value of k causes KNN to become slower [30].…”

HTTP header based phishing attack detection using machine learning

“…The mechanism is designed to generate rules automatically based on the layout similarity of website pages. Karim et al, 33 proposed a hybrid classifier based model havig both hard and soft voting to enhance anti-phishing technique. Further a canopy method is applied for feature selection with grid search optimization method in the proposed work.…”

“…El-Alfy et al 26 Niakanl Ahiji et al 27 Barlow et al 28 Al-Haija et al 29 Rao et al 30 Ubing et al 31 Mao et al 32 Karim et al 33…”

Assessment of existing cyber-attack detection models for web-based systems

“…More information and metrics are necessary to understand how a model truly performs. It is important to note that, there are limited studies on the application of DL techniques in specific cyber-attack detection domains, for instance, for phishing attacks [156], [176], [189]- [195].…”