LL-XSS: End-to-End Generative Model-based XSS Payload Creation

Abstract

In the realm of web security, there is a growing shift towards harnessing machine learning techniques for Cross-Site Scripting (XSS) vulnerability detection. This shift recognizes the potential of automation to streamline identification processes and reduce reliance on manual human analysis. An alternative approach involves security professionals actively executing XSS attacks to precisely pinpoint vulnerable areas within web applications, facilitating targeted remediation. Furthermore, there has been a growing interest in machine learning-based methods for creating XSS payloads in academic and research domains. In this research, we introduce a new model for generating XSS payloads, utilizing a combination of auto-regressive and generative AI models to craft malicious scripts intended to exploit potential vulnerabilities. Our approach to XSS vulnerability detection encompasses both frontend and backend code, providing organizations with a comprehensive means to enhance web application security.