Beyond the Veil: Analyzing Dark Web Threats with AI Mitigation

DOI

10.2991/978-94-6463-852-3_5How to use a DOI?

Keywords

Dark Web Security; Vulnerability Detection; AI-Driven Threat Mitigation; Onion Websites; Manual Vulnerability Verification

Abstract

Web The dark web has become significantly used for anonymous communication and commerce but has developed as a cyber-based threat environment. Because of the complex architecture, layers of encryption, and facade that onion sites provide, it is challenging to assess the security model of sites hosted on the dark web. This paper describes a tailored vulnerability scanner for testing and identifying potential security vulnerabilities in dark web-hosted applications. The proposed application can specifically detect impactful vulnerabilities, which include Cross-Site Scripting (XSS), Clickjacking, Cross-Origin Resource Sharing (CORS) issues and configuration problems, improper use of HTTP security headers, JavaScript-based exploits, as well as HTML Injection. The system is an automated scanner that applies tested definitions with manual verification to have high accuracy and reliability for detecting and reporting potential security vulnerabilities. The research assesses impact from the scanner using metrics for validated threats, misclassification alerts, and reliability. The results show 100% confirmation of validated vulnerabilities. The scanner also highlighted significantly less memory consumption compared to baseline metrics highlighting issues with low-power resources. This research helps to increase cybersecurity for dark web businesses with a practical, efficient solution for determining whether a website is vulnerable. Future work will concentrate on implementation of automated mitigations and optimization for large-scale dark web analysis. Furthermore, the findings of this research deliver lessons learned about secure dark web hosting and stress the value of proactive threat detection for reducing compromised solutions.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Malik Sadaf Allauddin
AU  - Prashant Lokhande
PY  - 2025
DA  - 2025/10/07
TI  - Beyond the Veil: Analyzing Dark Web Threats with AI Mitigation
BT  - Proceedings of the MULTINOVA: First International Conference on Artificial Intelligence in Engineering, Healthcare and Sciences (ICAIEHS- 2025)
PB  - Atlantis Press
SP  - 62
EP  - 82
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-852-3_5
DO  - 10.2991/978-94-6463-852-3_5
ID  - Allauddin2025
ER  -