By using a large dataset based on phishing URLs, attackers initiate attacks on the Internet. The aim of the study is to improve the detection of cyber hazards using different types of machine learning methods. These algorithms include Decision Tree, Linear Regression, Random Forest, 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 classifier, an ensemble technique. This model connects predictions with Random Forest Classifier and MLP Classifier as base classifiers. We have achieved it through carefully cross-fold validation and Grid Search Hyperparameter Optimization. As a meta-estimator, it appoints the LGBM classifier to reach the final prediction, which extends the project's ability to perform better classification. The effect of the model is evaluated using metrics including F1 score, recall, accuracy, and precision. The results show that the Hybrid LSD model effectively reduces the risk of phishing 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 through machine learning.
Keywords: Phishing attacks, Machine learning algorithms, Cyber threat detection, Hybrid LSD model, Cyber security measures.
How to cite this article: Tata RK, Krishna TSSS. A phishing detection system using URL-based hybrid machine learning. Int J Drug Deliv Technol. 2026;16(3s): 1016-1024; DOI: 10.25258/ijddt.16.3s.122
Source of support: None.
Conflict of interest: None