Offensive AI: Enhancing Directory Brute-forcing Attack with the Use of Language Models
Preprint
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%.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- AI Based Directory Discovery Attack and Prevention of the Medical Systems2022
- The Threat of Offensive AI to OrganizationsComputers & Security, 2022
- A feature-vector generative adversarial network for evading PDF malware classifiersInformation Sciences, 2020
- Recurrent GANs Password Cracker For IoT Password Security EnhancementSensors, 2020
- Language Models as Knowledge Bases?2019