EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Beyond performance metrics: evaluating the unique value of generative AI in hybrid cybersecurity threat detection

Juan Antonio González-Ramos, Pablo Chamoso

Frontiers in Big Data · 24.04.2026 · 9

DOI: 10.3389/fdata.2026.1768366 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Big Data, online erschienen am 24.04.2026. Verfasst von Juan Antonio González-Ramos und 1 weiteren Autor:innen. Beteiligte Einrichtung: Computing and Automation Department, University of Salamanca, Salamanca, Spain. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

This study examines the role of generative artificial intelligence (GenAI) in cybersecurity threat detection, focusing on its usefulness in workflows that support human decision-making.

Methods

Experiments were performed on the BODMAS dataset (134,435 samples) and a smaller exploratory subset of UNSW-NB15. State-of-the-art machine learning (ML) classifiers were compared with a zero-shot large language model (LLM) using standard classification metrics, while also considering latency, cost, and hallucination risk.

Results

ML classifiers consistently outperformed the LLM-based system on standard detection metrics. However, the LLM showed value in cases of ambiguity, where it could provide short plain-language explanations, organize alert-related context, and generate initial interpretations for instances that did not match learned classes.

Discussion

GenAI is unlikely to replace ML-based detection methods, but it can provide useful interpretive support for ambiguous or unfamiliar alerts. A hybrid pipeline is therefore proposed, in which ML handles high-confidence and time-sensitive decisions, while the LLM is used selectively for low-confidence cases or when explanatory support is needed. Human oversight remains necessary to address hallucination risk and ensure reliability.

Schlagwörter

Stichwörter der Autor:innen

cybersecurityexplainable AIgenerative artificial intelligencehybrid systemslarge language modelsmachine learningthreat detectionzero-shot learning

Autor:innen und Institutionen

  • Computing and Automation Department, University of Salamanca, Salamanca, Spain.
  • Computing and Automation Department, BISITE Research Group, University of Salamanca, Salamanca, Spain.

Zitieren

APA

González-Ramos, J. A., & Chamoso, P. (2026). Beyond performance metrics: evaluating the unique value of generative AI in hybrid cybersecurity threat detection. Frontiers in Big Data, 9. https://doi.org/10.3389/fdata.2026.1768366

Vancouver

González-Ramos JA, Chamoso P. Beyond performance metrics: evaluating the unique value of generative AI in hybrid cybersecurity threat detection. Frontiers in Big Data. 2026;9. doi:10.3389/fdata.2026.1768366

BibTeX
@article{GonzlezRamos2026,
  author = {González-Ramos, Juan Antonio and Chamoso, Pablo},
  title = {Beyond performance metrics: evaluating the unique value of generative AI in hybrid cybersecurity threat detection},
  journal = {Frontiers in Big Data},
  year = {2026},
  volume = {9},
  doi = {10.3389/fdata.2026.1768366}
}
Kostenlos starten →