University of Twente Student Theses
As of Friday, 8 August 2025, the current Student Theses repository is no longer available for thesis uploads. A new Student Theses repository will be available starting Friday, 15 August 2025.
Towards Accurate and Optimized Booter Website Classification : Evaluating AI Models for Law Enforcement
Setty, Narendra (2025) Towards Accurate and Optimized Booter Website Classification : Evaluating AI Models for Law Enforcement.
|
PDF
485kB |
| Abstract: | The proliferation of booter websites offering DDoS-for-hire services poses a significant cybersecurity threat by enabling malicious actors to disrupt online services with minimal technical expertise. This problem is compelling due to the increasing sophistication of these platforms and the limitations of existing detection methods, which rely on predefined feature sets and often overlook complex semantic patterns or visual elements. My solution evaluates text-based and multimodal large language models (LLMs), achieving high accuracy (F1-score and accuracy of 100%) through optimized prompt engineering and semantic text analysis, surpassing traditional approaches. Additionally, the study leverages LLMs to analyze archived snapshots of booter websites that have been taken down, expanding the dataset and improving detection robustness. These findings provide law enforcement with practical, cost-effective guidelines for implementing scalable and reliable booter detection systems, enhancing their ability to combat DDoS threats efficiently |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science BSc (56964) |
| Link to this item: | https://purl.utwente.nl/essays/107414 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page