Cross-site detection system using Support Vector Machine / Ahmad A’limmuddin Bahrim

A form of security issue called cross-site scripting (XSS) enables attackers to insert malicious code into a website. When a user accesses the website, the malicious code may steal personal data or carry out other undesirable actions. XSS attacks can be classified as stored, reflected, or DOM-based. With the help of machine learning techniques like Support Vector Machines (SVM), these attacks, which are frequent, can be stopped. A cross-site detection system for XSS scripting was created in this work utilising the Support Vector Machine (SVM) technique. Support Vector Machine (SVM) is a technique used to determine whether XSS scripts have been implanted in a website or not. Six different research approaches, including a preliminary study, requirement analysis, data gathering, design, implementation, evaluation, and documentation, were used to construct this system efficiently. The system's stated objectives could be successfully attained at the end of the study thanks to the tight alignment of these approaches with those goals. Next, the dataset used for this study is dataset named “Cross site scripting XSS dataset for Deep learning” can be download from website online which is Kaggle contributed by Syed Saqlain Hussain Shah. The dataset contains Cross site scripting attack (XSS) data along with benign data. The research is significant in addressing the serious threats posed by cross-site assaults to the security and integrity of web systems, and in contributing to the development of effective detection and mitigation strategies.