Skip to main navigation Skip to search Skip to main content

Preliminary Study of LLM-Based Wordlist Generation for Validating Broken Web Access Control

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The public websites have become targets for hackers, resulting in reputational and financial losses. A considerable portion of cybersecurity issues arise from web attacks. Web vulnerabilities can often be traced back to web servers that have been misconfigured by unskilled administrators. Broken web access control leads to unauthorized access to sensitive resources and data. A wordlist-based testing is used to identify such vulnerabilities. This paper will discuss the threats posed by such misconfigured web services and explore how the LLM scanning approach generates wordlists, thereby enhancing the efficiency of identifying vulnerabilities within the web server. The study concluded that using different LLM models, in conjunction with summarization, role-playing, and Chain-of-Thought (CoT) techniques, enhances the discovery of web paths.

Original languageEnglish
Title of host publicationProceedings of the IEEE Region 10 Conference 2024
Subtitle of host publicationArtificial Intelligence and Deep Learning Technologies for Sustainable Future, TENCON 2024
EditorsBin Luo, Sanjib Kumar Sahoo, Yee Hui Lee, Christopher H T Lee, Michael Ong, Arokiaswami Alphones
Pages1088-1091
Number of pages4
ISBN (Electronic)9798350350821
DOIs
Publication statusPublished - 2024
Event2024 IEEE Region 10 Conference, TENCON 2024 - Singapore, Singapore
Duration: 1 Dec 2024 → 4 Dec 2024

Publication series

NameIEEE Region 10 Annual International Conference, Proceedings/TENCON
ISSN (Print)2159-3442
ISSN (Electronic)2159-3450

Conference

Conference2024 IEEE Region 10 Conference, TENCON 2024
Country/TerritorySingapore
CitySingapore
Period1/12/24 → 4/12/24

Keywords

  • Computer Hacking
  • Large Language Models
  • Unauthorized Access
  • Web Attacks

Fingerprint

Dive into the research topics of 'Preliminary Study of LLM-Based Wordlist Generation for Validating Broken Web Access Control'. Together they form a unique fingerprint.

Cite this