<![CDATA[This research aims to compare Machine Learning models that effectively detect SQL Injection attacks in security systems. The dataset was col lected from the Kaggle resource published by Syed Saqlain Hussain Shah, the dataset with the highest upvotes in the SQL Injection category. The models developed include Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Logistic Regression (LR). The research process includes separating the data into 70% training and 30% test data, model training, testing model effectiveness, and implementing preventive measures against SQL Injection attacks. The research results show that the SVM model has an accuracy rate of 99.82%, precision of 99.88%, and recall (Sensitivity) of 99.34%. KNN obtained an accuracy rate of 79.28%, a precision of 98.38%, and a recall (Sensitivity) of 73.31%. LR obtained an accuracy rate of 98.99%, precision of 99.94%, and recall (Sensitivity) of 98.70%. Using a Machine Learning approach, this research improves system security against SQL Injection attacks.]]>
Copyrights © 2024
