An Approach for Efficient and Accurate Phishing Website Prediction Using Improved ML Classifier Performance for Feature Selection
Journal Title: International Journal of Experimental Research and Review - Year 2024, Vol 40, Issue 4
Abstract
The article discusses the use of machine learning (ML) to combat phishing websites, which are deceptive sites that mimic trusted entities to steal sensitive information. This is why the continued invention of methods of identifying and counteracting phishing threats is beneficial. Such attacks pose significant risks to the integrity of online security. To enhance the success rate and specificity of predicting phishing websites, this study proposes a new approach that utilizes machine learning algorithms. To enhance the methods mentioned above and achieve better results in classification and better prediction of customer behaviour, the main points exposed to further transformations are increasing classifier accuracy and selecting an optimal feature space. Traditional anti-phishing strategies like blacklisting and heuristic searches often have slow detection times and high false positive rates. The article introduces a novel feature selection method to extract highly correlated features from datasets, thereby enhancing classifier accuracy. Using six feature selection techniques on a phishing dataset, it evaluates eight classifiers, including SVM, Logistic Regression, Random Forest, and others. The study finds that the Random Forest classifier combined with the Chi-2 feature selection method significantly improves model accuracy, achieving up to 96.99%.
Authors and Affiliations
Anjaneya Awasthi, Noopur Goel
Keywords
Related Articles
- EP ID EP739924
- DOI 10.52756/ijerr.2024.v40spl.006
- Views 91
- Downloads 1
Urban adult overweight and obesity prevalence in North Dum Dum, West Bengal, India
Obesity impacts most of the population, and many countries are predicted to raise the prevalence of adults affected by obesity (OB) and related disorders during the recent decades. OB is uninterruptedly increasing at a s...
A Green Raman Spectroscopic Assay Method for The Quantification of Tranexamic Acid in Pharmaceutical Formulations
Tranexamic acid (TXA) is a widely used antifibrinolytic agent that is used to prevent and treat excessive bleeding. Current analytical methods for TXA are often time-consuming and require the use of toxic solvents. Raman...
Application of Genetic Algorithms for Medical Diagnosis of Diabetes Mellitus
The system of glucose-insulin control and associated problems in diabetes mellitus were studied by mathematical modeling. It is a helpful theoretical tool for understanding the basic concepts of numerous distinct medical...
Factors Determining Household Waste Segregation Behaviour: An Indian Case Study
Waste represents used things or materials that are no longer required or wanted. These articles are cast off as they have stopped working or because they have ceased to be of value. Human settlements inevitably generate...
Recent progress in organic nano-composites: Synthesis and treatments for use as active layers in electronic devices
The present work represents an overview for organic materials and their nano-structuration using carbon nano-tubes. Particular attention is allowed to the polyaniline polymer and single walled carbon nanotubes which are...