| Abstrakt: |
Today's digital world depends on web applications via the Internet to provide services and connect institutions and individuals in various fields such as paying bills, completing daily transactions, commercial exchange, banking transactions, the medical field, and much more. These services are rapidly increasing, and web applications are exposed to more attacks because of this increase. These attacks lead to significant losses for organizations and individuals in providing services due to the loss of confidentiality, integrity, and availability of customer information. One of the most common attacks via web applications is SQL injection, enabling an attacker to gain unauthorized access to data. This study focuses on detecting SQL injection attacks using the support vector machine algorithm with Principal Component Analysis and a comparison with a group of machine learning algorithms such as Random Forests, Decision Tree, and Naive Bayes. Whereby building the support vector machine model on a data set containing 18900 samples, it has been found that the model achieved a prediction accuracy of 97.35 in addition to a high speed, which amounted to 0.265 parts of a second, which is more predictable than the models mentioned in the related works. [ABSTRACT FROM AUTHOR] |
