EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A hybrid transformer-BiLSTM model optimized with Firefly Algorithm for network traffic anomaly detection

Debiao Luo iD, Weijie Wang, Xinyue Liu, Wen Yang, Ke Hu, Jia Zhang

PLOS One · 17.06.2026 · 21 (6) · e0341920

DOI: 10.1371/journal.pone.0341920 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 17.06.2026. Verfasst von Debiao Luo und 5 weiteren Autor:innen. Beteiligte Einrichtung: Information Network Center, Chengdu University, Chengdu, China. Hauptthemen laut MEDLINE: Algorithms. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Network Traffic Anomaly Detection (NTAD) is essential for proactive cyber defense against increasingly sophisticated threats. This paper presents a data-driven framework that integrates adaptive signal decomposition, a hybrid attention-recurrent architecture, and metaheuristic optimization for timely anomaly prediction. Raw traffic sequences are first preprocessed via Empirical Mode Decomposition (EMD) to mitigate non-stationarity and suppress noise, yielding denoised intrinsic mode functions. The refined signal is then modeled by a hybrid deep network that couples a multi-head self-attention mechanism—capturing global, long-range dependencies—with a Bidirectional Long Short-Term Memory (BiLSTM) network that encodes bidirectional temporal dynamics. To circumvent the sensitivity of deep models to hyperparameter selection, the Firefly Algorithm (FA) is employed for automated, population-based optimization. Extensive evaluations on benchmark datasets demonstrate that the proposed EMD-FA-Transformer-BiLSTM model attains state-of-the-art performance, outperforms baseline and state-of-the-art models across all evaluated metrics, with statistically significant improvements in both regression error and classification F 1 -score.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsLong Short Term MemoryAnimalsPrediction Algorithms

Autor:innen und Institutionen

  • Information Network Center, Chengdu University, Chengdu, China.
  • Library, Chengdu University, Chengdu, China.

ORCID-Profile: Debiao Luo

Zitieren

APA

Luo, D., Wang, W., Liu, X., Yang, W., Hu, K., & Zhang, J. (2026). A hybrid transformer-BiLSTM model optimized with Firefly Algorithm for network traffic anomaly detection. PLOS One, 21(6), e0341920. https://doi.org/10.1371/journal.pone.0341920

Vancouver

Luo D, Wang W, Liu X, Yang W, Hu K, Zhang J. A hybrid transformer-BiLSTM model optimized with Firefly Algorithm for network traffic anomaly detection. PLOS One. 2026;21(6):e0341920. doi:10.1371/journal.pone.0341920

BibTeX
@article{Luo2026,
  author = {Luo, Debiao and Wang, Weijie and Liu, Xinyue and Yang, Wen and Hu, Ke and Zhang, Jia},
  title = {A hybrid transformer-BiLSTM model optimized with Firefly Algorithm for network traffic anomaly detection},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {6},
  pages = {e0341920},
  doi = {10.1371/journal.pone.0341920}
}
Kostenlos starten →