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