A Novel Approach For Phishing Detection System Using Hybrid Data Mining Techniques

Abstract

Abstract: By using a large dataset based on the fishing url, they begin attacks on the Internet. The aim of the study is to improve detection of cyber hazards using different types of machine learning methods. These algorithms include “Decision Tree [4], Linear Regression [4], Random Forest [4], Naive Bayes, Gradient Boosting Classifier, Support Vector Classifier, and a new hybrid LSD model”. We have used a hybrid model by combining the predictions of many individual models, such as a stacking classify, a ensemble technique. This model connects predictions with “Random Forest [4] Classifier and MLP Classifier as base classifiers”. We have achieved it through carefully cross- fold validation and Grid Search Hyper parameter Optimization. As a meta-estimator, it appoints the LGBM classification to reach the final prediction, which extends the project's ability to perform better classification. The effect of the model is evaluated using matrix including F1 score, recalling, accuracy and accuracy. The results show that the Hybrid LSD model effectively reduces the risk of fish attacks and provides strong protection against the ever -changing cyber threats. This study contributes to the development of better cyber security measures, and shows how you can improve the safety of the Internet by learning machine.