Authors:
Ciprian Paduraru
1
;
Catalina Patilea
1
and
Alin Stefanescu
1
;
2
Affiliations:
1
Department of Computer Science, University of Bucharest, Romania
;
2
Institute for Logic and Data Science, Romania
Keyword(s):
Large Language Models, Cybersecurity Assistant, Security Officers, Agentic AI, Fine-Tuning, Retrieval Augmented Generation.
Abstract:
Robust cybersecurity measures are essential to protect complex information systems from a variety of cyber threats, which requires sophisticated security solutions. This paper explores the integration of Large Language Models (LLMs) to improve cybersecurity operations within Security Operations Centers (SOCs). The proposed framework has a modular plugin architecture where Agentic AI controls the information flow, in-cludes Retrieval Augmented Generation (RAG), protection methods for human-chatbot interactions and tools for managing tasks such as database interactions, code generation and execution. By utilizing these techniques, the framework aims to streamline the workflows of SOC analysts, allowing them to focus on critical tasks rather than redundant activities. The study also explores the dynamic customization of LLMs based on client data, user experience, potential risks and language preferences to ensure a user-centric approach. The results show improvements in efficiency and e
ffectiveness and highlight the potential of LLMs in cybersecu-rity applications.
(More)