Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.

Enhancing Security Operations Center: Wazuh Security Event Response with Retrieval-Augmented-Generation-Driven Copilot

Open access

Abstract

The sophistication of cyberthreats demands more efficient and intelligent tools to support Security Operations Centers (SOCs) in managing and mitigating incidents. To address this, we developed the Security Event Response Copilot (SERC), a system designed to assist analysts in responding to and mitigating security breaches more effectively. SERC integrates two core components: (1) security event data extraction using Retrieval-Augmented Generation (RAG) methods, and (2) LLM-based incident response guidance. This paper specifically utilizes Wazuh, an open-source Security Information and Event Management (SIEM) platform, as the foundation for capturing, analyzing, and correlating security events from endpoints. SERC leverages Wazuh’s capabilities to collect real-time event data and applies a RAG approach to retrieve context-specific insights from three vectorized data collections: incident response knowledge, the MITRE ATT&CK framework, and the NIST Cybersecurity Framework (CSF) 2.0. This integration bridges strategic risk management and tactical intelligence, enabling precise identification of adversarial tactics and techniques while adhering to best practices in cybersecurity. The results demonstrate the potential of combining structured threat intelligence frameworks with AI-driven models, empowered by Wazuh’s robust SIEM capabilities, to address the dynamic challenges faced by SOCs in today’s complex cybersecurity environment.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/s25030870

Cites

36 of 36 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Event security management lifecycle (adapted from [22]).
Figure 1 Event security management lifecycle (adapted from [22]).CC BY · PubMed Central
Figure 2 Overview of Retrieval-Augmented Generation.
Figure 2 Overview of Retrieval-Augmented Generation.CC BY · PubMed Central
Figure 3 Augmentation process illustration.
Figure 3 Augmentation process illustration.CC BY · PubMed Central
Figure 4 Event security data extraction pipeline.
Figure 4 Event security data extraction pipeline.CC BY · PubMed Central
Figure 5 Security Event Response Copilot (SERC) Workflow.
Figure 5 Security Event Response Copilot (SERC) Workflow.CC BY · PubMed Central
Figure 6 Copilot embedded into Wazuh with custom interface.
Figure 6 Copilot embedded into Wazuh with custom interface.CC BY · PubMed Central
Figure 7 High-level simulation workflow.
Figure 7 High-level simulation workflow.CC BY · PubMed Central
Figure 8 Attack simulation scenario.
Figure 8 Attack simulation scenario.CC BY · PubMed Central
Figure 9 Model performance from various attacks using cosine similarity.
Figure 9 Model performance from various attacks using cosine similarity.CC BY · PubMed Central
Figure 10 Model performance from various attacks using BERTScore: precision.
Figure 10 Model performance from various attacks using BERTScore: precision.CC BY · PubMed Central
Figure 11 Model performance from various attacks using BERTScore: recall.
Figure 11 Model performance from various attacks using BERTScore: recall.CC BY · PubMed Central
Figure 12 Model performance from various attacks using BERTScore: F1.
Figure 12 Model performance from various attacks using BERTScore: F1.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 22 references

Research works printed but not linked: 8

  1. Kaliyaperumal, 2021, The Evolution of Security Operations and Strategies for Building an Effective SOC, ISACA J., 5, 1
  2. Islam, 2024, The Application of MITRE ATT&CK Framework in Mitigating Cybersecurity Threats in the Public Sector, Issues Inf. Syst., 25, 62
  3. eWeek (2024, December 18). QRadar vs. Splunk: SIEM Tools Review|eWeek. Available online: https://www.eweek.com/security/splunk-vs-ibm-qradar-siem-head-to-head/.
  4. Dunsin, 2023, A Comprehensive Analysis of the Role of Artificial Intelligence and Machine Learning in Modern Digital Forensics and Incident Response Article info, Forensic Sci. Int. Digit. Investig., 48, 301675
  5. Sadighian, 2023, MITRE ATT&CK: State of the Art and Way Forward, ACM Comput. Surv., 57, 1
  6. Fortinet (2023). Meet Fortinet Advisor, a Generative AI Assistant that Accelerates Threat Investigation and Remediation, Fortinet. Available online: https://www.fortinet.com/corporate/about-us/newsroom/press-releases/2023/fortinet-advisor-a-generative-ai-assistant-accelerating-threat-investigation-and-remediation.
  7. Landauer, M., Mayer, K., Skopik, F., Wurzenberger, M., and Kern, M. (2024). Red Team Redemption: A Structured Comparison of Open-Source Tools for Adversary Emulation. arXiv.
  8. Qdrant (2024, December 18). GitHub-Qdrant/Qdrant-Rag-Eval: This Repo Is the Central Repo for All the RAG Evaluation Reference Material and Partner Workshop. Available online: https://qdrant.tech/documentation/overview/.

Cited by

See all 16

Metadata

Authors
Ismail, Kurnia, R., Widyatama, F., Wibawa, I. M., Brata, Z. A., Ukasyah, Nelistiani, G. A., & Kim, H.
Affiliations
  • School of Computer Science and Engineering, Pusan National University, Busan 46241, Republic of Korea
  • SmartM2M Co., Ltd., 701, 702, Building A, Centum Skybiz, 97 Centumjungang-ro, Haeundae-gu, Busan 48058, Republic of Korea
  • Pusan National University (KR)
Corresponding author
Kim, Howon
Venue
Sensors
Publisher
MDPI AG
Published
2025-01-31
Volume
25
Issue
3
Pages
870
ISSN
1424-8220 (ISSN-L)
OpenAlex
W4407006955
Cited by
16
References
22
Citations by year
2026: 12 · 2025: 4
FWCI
6.72
Type
journal article
Language
en
Open access
Locations
  • Sensors (publishedVersion, cc-by)
  • Preprints.org (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Korea government(MSIT) (RS-2024-00402782)
Topics
  • Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
  • Physical Sciences › Computer Science › Information Systems › Information and Cyber Security
  • Physical Sciences › Computer Science › Information Systems › Digital and Cyber Forensics
Keywords
security operations center, incident response, Wazuh, security information and event management, retrieval-augmented generation, large language models, security event analysis, MITRE ATT&CK, NIST Cybersecurity Framework, threat intelligence, endpoint security, AI copilots

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Enhancing Security Operations Center: Wazuh Security Event Response with Retrieval-Augmented-Generation-Driven Copilot. https://app.cochat.ai/papers/10.3390/s25030870
The paper
Ismail, Kurnia, R., Widyatama, F., Wibawa, I. M., Brata, Z. A., Ukasyah, Nelistiani, G. A., & Kim, H. (2025). Enhancing Security Operations Center: Wazuh Security Event Response with Retrieval-Augmented-Generation-Driven Copilot. Sensors. https://doi.org/10.3390/s25030870

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.