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.
AI-Driven Analysis of Conti Ransomware Leaks for Perpetrator Identification and Victim Profiling
Gladkov, Dan (2025) AI-Driven Analysis of Conti Ransomware Leaks for Perpetrator Identification and Victim Profiling.
|
PDF
551kB |
| Abstract: | The rapidly evolving nature of cybercrime, expedited by technological advancements, particularly in Artificial Intelligence (AI), has posed a significant challenge for law enforcement and a critical point for digital forensics. Cybercriminal investigations have started to involve large volumes of different types of data, pushing traditional, manual, and human-centered methods of investigation to their limits. Experts have begun using AI in their work, but only for specific tasks and it is still heavily human-controlled. Research on the topic has also been largely speculative, with few practical solutions. This research proposes the development of an AI-driven investigative Agent, which will perform a comprehensive data processing cycle, including data parsing, translation, enrichment with public information, and analysis. It will be built following the LangChain or CrewAI frameworks, and powered by a publicly available Large Language Model (LLM) from Ollama, accessible at its GitHub Repository. The Agent will be tasked with leaked internal communications from the Conti ransomware group. The analysis will focus on profiling perpetrators and victims to construct a structured understanding of the group’s operations. This research aims to demonstrate the potential and benefits of deploying AI Agents within law enforcement and digital forensics, keeping up with the digital breakthroughs that empower cybercriminals. |
| 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/107450 |
| 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