Identification of pharming in communication networks using ensemble learning

Pharming scams are carried out by exploiting the DNS as main weapon while phishing attacks employ spoofed websites that appear to be legitimate internet users. Phishing makes use of baits such fake links but pharming leverages and negotiates on server move redirect users a simulated website.Having seen several challenges through resulting into vulnerable websites, personal emails accounts social media, usage reliability calls for caution. Against this backdrop, work aims at enhancing detection strategies adopting machine learning classification algorithms. To further obtain best results, an ensemble approach was adopted. The algorithms used include K-Nearest Neighbors (KNN), Decision Tree, Random Forest, Gaussian Naive Bayes, Logistic Regression, Support Vector Machine, Adaptive Boosting, Gradient Extra Trees Classifier. During testing process, classifiers were tested against four popular metrics: accuracy, recall, precision, F1 score, Log loss. results demonstrate performance all used, well their relationships. model included Neighbors, Boosting Classifier, AdaBoost Forest produced after evaluating them two datasets. Classifiers showed better classifiers, with mean accuracies 0.932 0.939, respectively each datasets when compared 0.476 0.519 obtained Bayes.