Publication detail

Enhancing Security Monitoring with AI-Enabled Log Collection and NLP Modules on a Unified Open Source Platform

SAFONOV, Y. ŽERNOVIČ, M.

Original Title

Enhancing Security Monitoring with AI-Enabled Log Collection and NLP Modules on a Unified Open Source Platform

Type

conference paper

Language

English

Original Abstract

The number of computer attacks continues to increase daily, posing significant challenges to modern security administrators to provide security in their organizations. With the rise of sophisticated cyber threats, it is becoming increasingly difficult to detect and prevent attacks using traditional security measures. As a result, security monitoring solutions such as Security Information and Event Management (SIEM) have become a critical component of modern security infrastructures. However, these solutions still face limitations, and administrators are constantly seeking ways to enhance their capabilities to effectively protect their cyber units. This paper explores how advanced deep learning techniques can help boost security monitoring capabilities by utilizing them throughout all stages of log processing. The presented platform has the potential to fundamentally transform and bring about a significant change in the field of security monitoring with advanced AI capabilities. The study includes a detailed comparison of modern log collection platforms, with the goal of determining the most effective approach. The key benefits of the proposed solution are its scalability and multipurpose nature. The platform integrates an open source solution and allows the organization to connect any event log sources or the entire SIEM solution, normalize and filter data, and use this data to train and deploy different AI models to perform different security monitoring tasks more efficiently.

Keywords

correlation; deep learning; log processing; meta key extraction; natural language processing; SIEM; question answering

Authors

SAFONOV, Y.; ŽERNOVIČ, M.

Released

25. 4. 2023

Publisher

Brno University of Technology; The Faculty of Electrical Engineering and Communication

Location

Brno

ISBN

978-80-214-6154-3

Book

Proceedings II of the 29th Conference STUDENT EEICT 2023 Selected Papers

Edition

1

ISBN

2788-1334

Periodical

Proceedings II of the Conference STUDENT EEICT

State

Czech Republic

Pages from

217

Pages to

221

Pages count

4

URL

BibTex

@inproceedings{BUT184351,
  author="Yehor {Safonov} and Michal {Žernovič}",
  title="Enhancing Security Monitoring with AI-Enabled Log Collection and NLP Modules on a Unified Open Source Platform",
  booktitle="Proceedings II of the 29th Conference STUDENT EEICT 2023 Selected Papers",
  year="2023",
  series="1",
  journal="Proceedings II of the Conference STUDENT EEICT",
  pages="217--221",
  publisher="Brno University of Technology; The Faculty of Electrical Engineering and Communication",
  address="Brno",
  doi="10.13164/eeict.2023.217",
  isbn="978-80-214-6154-3",
  issn="2788-1334",
  url="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2023_sbornik_2_v2.pdf"
}