Offensive AI: Enhancing Directory Brute-forcing Attack with the Use of Language Models

TL;DR

This paper introduces a novel AI-driven framework using language models to significantly improve the efficiency of directory brute-forcing attacks in web vulnerability assessments, outperforming traditional methods.

Contribution

The work presents the first application of language models to enhance directory enumeration in web security, demonstrating substantial performance gains over existing brute-force techniques.

Findings

969% average performance increase with LM-based attack

Effective in diverse web application domains

Outperforms traditional brute-force methods

Abstract

Web Vulnerability Assessment and Penetration Testing (Web VAPT) is a comprehensive cybersecurity process that uncovers a range of vulnerabilities which, if exploited, could compromise the integrity of web applications. In a VAPT, it is common to perform a \textit{Directory brute-forcing Attack}, aiming at the identification of accessible directories of a target website. Current commercial solutions are inefficient as they are based on brute-forcing strategies that use wordlists, resulting in enormous quantities of trials for a small amount of success. Offensive AI is a recent paradigm that integrates AI-based technologies in cyber attacks. In this work, we explore whether AI can enhance the directory enumeration process and propose a novel Language Model-based framework. Our experiments -- conducted in a testbed consisting of 1 million URLs from different web application domains (universities, hospitals, government, companies) -- demonstrate the superiority of the LM-based attack, with an average performance increase of 969%.