CoChat

Deep learning with leagues championship algorithm based intrusion detection on cybersecurity driven industrial IoT systems

Open access
Alotaibi, Saud S., Alghamdi, Turki Ali · 2025 · Scientific Reports

The DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.

Abstract

The Internet of Things (IoT) presents significant advantages to day-to-day life across a wide range of application domains, including healthcare automation, transportation, and smart environments. However, owing to the constraints of limited resources and computation abilities, IoT networks are subject to different cyber-attacks. Incorporating IDS into the cybersecurity-driven IIoT process contains cautious deployment, planning, and progressing management. Cybersecurity is crucial for the protection of sensitive data, safeguarding the privacy of users, and securing important substructures from malicious activities attempting unauthorized access or triggering interferences. Cyberattack detection performs a vital role in this defense scheme, employing advanced technologies like deep learning (DL) for analysing digital activities in real time. With the help of recognizing and responding to possible cyber-attacks quickly, cyberattack detection not only mitigates risks but reinforces the overall flexibility of the digital ecosystem against developing security challenges. This study presents a League Championship Algorithm Feature Selection with Optimal Deep Learning based Cyberattack Detection (CLAFS-ODLCD) technique for securing the digital ecosystem. The CLAFS-ODLCD technique focuses on the recognition and classification of cyberattacks in the IoT infrastructure. To achieve this, the CLAFS-ODLCD method utilizes the linear scaling normalization (LSN) approach for data pre-processing. Furthermore, the CLAFS-ODLCD method employs the CLAFS approach to choose optimal feature subset. Moreover, the detection and classification of the cyberattacks are accomplished by implementing the stacked sparse autoencoder (SSAE) approach. Finally, the hunger games search (HGS) optimizer is employed for optimum hyperparameter selection. The empirical analysis of the CLAFS-ODLCD method is examined under the WSN-DS dataset. The comparison study of the CLAFS-ODLCD method portrayed a superior accuracy value of 99.48% over existing models.

Overview

CoChat Summary

TL;DR

The paper proposes CLAFS-ODLCD, a pipeline combining LSN normalization, League Championship Algorithm feature selection, stacked sparse autoencoder classification, and hunger games search hyperparameter tuning for intrusion detection in IIoT/IoT systems. On the WSN-DS dataset it reports up to 99.48% average accuracy and 1.09 s computational time, outperforming compared models.

Key findings

  • On WSN-DS with 80% training and 20% testing, CLAFS-ODLCD reports averages of 99.48%, 92.51%, 99.10%, 91.02%, 95.81%, and Kappa of 95.87%; with 20% testing it reports 99.45%, 92.17%, 99.06%, 90.48%, 95.61%, and Kappa of 95.69%.
  • With 70% training and 30% testing, it reports averages of 99.13%, 82.88%, 97.36%, 85.15%, 90.12%, and Kappa of 90.18%; with 30% testing it reports 99.13%, 83.18%, 97.42%, 85.21%, 90.30%, and Kappa of 90.36%.
  • In comparison, the method reaches a maximal 99.48%, 92.51%, 99.10%, and 91.02%, and completes tasks in 1.09 s versus FL-LIDS at 8.09 s, CNN-BiLSTM-Attention at 5.22 s, and SCADA at 6.31 s, reducing computational overhead by approximately 70 to 85 percent.
  • Ablation results show the full CLAFS-ODLCD at 99.48%, 92.51%, 99.10%, and 91.02%; SSAE at 98.91%, 91.89%, 98.35%, and 90.43%; HGS at 98.26%, 91.29%, 97.70%, and 89.85%; and LSN at 97.61%, 90.75%, 97.12%, and 89.32%.

Methods

  • The proposed CLAFS-ODLCD technique uses LSN-based data normalization, CLA-based feature selection, SSAE-based classification, and HGS-based hyperparameter tuning.
  • Validation uses the WSN-DS dataset with 374,661 samples and 5 classes, evaluated under 80%TRAPH:20%TESPH and 70%TRAPH:30%TESPH splits; implementation runs on Python 3.6.5 with an i5-8600k CPU, 4GB GPU, 16GB RAM, 250GB SSD, and 1TB HDD, using a 0.01 learning rate, ReLU, 50 epochs, 0.5 dropout, and batch size 5.
  • Main analyses include confusion matrices, training/validation accuracy and loss curves, PR and ROC curves, comparison with existing models, computational time comparison, and an ablation study.

Limitations

  • The paper does not explicitly state limitations of the proposed CLAFS-ODLCD method.
  • Evident from the text: validation is limited to the WSN-DS dataset, with no cross-dataset or real IIoT deployment validation reported.
  • Evident from the text: several metric labels and equations/tables are incomplete in the provided text, making some reported averages hard to map to named metrics; the paper also notes general challenges for existing models such as computational complexity, scalability, adaptability, and interpretability, but does not test these for its own method.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1038/s41598-025-15464-0

Cites

30 of 30 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Fig. 1 Working flow of CLAFS-ODLCD method.
Fig. 1 Working flow of CLAFS-ODLCD method.CC BY · PubMed Central
Fig. 2 Architecture of SSAE.
Fig. 2 Architecture of SSAE.CC BY · PubMed Central
Fig. 3 Confusion matrices of a, b 80%TRAPH:20%TESPH and c, d 70%TRAPH:30%TESPH.
Fig. 3 Confusion matrices of a, b 80%TRAPH:20%TESPH and c, d 70%TRAPH:30%TESPH.CC BY · PubMed Central
Fig. 4 Average of the CLAFS-ODLCD model on 80%TRAPH and 20%TESPH.
Fig. 4 Average of the CLAFS-ODLCD model on 80%TRAPH and 20%TESPH.CC BY · PubMed Central
Fig. 5 Average of the CLAFS-ODLCD method under 70%TRAPH and 30%TESPH.
Fig. 5 Average of the CLAFS-ODLCD method under 70%TRAPH and 30%TESPH.CC BY · PubMed Central
Fig. 6 Acc{u}_{y} curve of the CLAFS-ODLCD method at 80%TRAPH and 20%TESPH.
Fig. 6 Acc{u}_{y} curve of the CLAFS-ODLCD method at 80%TRAPH and 20%TESPH.CC BY · PubMed Central
Fig. 7 Loss curve of the CLAFS-ODLCD approach under 80%TRAPH and 20%TESPH.
Fig. 7 Loss curve of the CLAFS-ODLCD approach under 80%TRAPH and 20%TESPH.CC BY · PubMed Central
Fig. 8 PR curve of the CLAFS-ODLCD approach under 80%TRAPH and 20%TESPH.
Fig. 8 PR curve of the CLAFS-ODLCD approach under 80%TRAPH and 20%TESPH.CC BY · PubMed Central
Fig. 9 ROC curve of the CLAFS-ODLCD approach under 80%TRAPH and 20%TESPH.
Fig. 9 ROC curve of the CLAFS-ODLCD approach under 80%TRAPH and 20%TESPH.CC BY · PubMed Central
Fig. 10 Comparative outcomes of the CLAFS-ODLCD model with existing techniques.
Fig. 10 Comparative outcomes of the CLAFS-ODLCD model with existing techniques.CC BY · PubMed Central
Fig. 11 CT analysis of the CLAFS-ODLCD methodology with existing models.
Fig. 11 CT analysis of the CLAFS-ODLCD methodology with existing models.CC BY · PubMed Central
Fig. 12 Ablation study results comparing CLAFS-ODLCD method with existing techniques.
Fig. 12 Ablation study results comparing CLAFS-ODLCD method with existing techniques.CC BY · PubMed Central

Verification

Claims the paper makes

0 Valid · 0 Not valid · 0 Not checked · 29 Own results and interpretations

11 more claims

Create a free account to see all 29 claims and every source verdict.

See all claims — free account
  • It may state two separate claims as one. 9
  • Probably not a substantial claim. 6

Create a free account to see these claims.

Citations

Cites

Show all 30 references

Research works printed but not linked: 3

  1. Abou-Elasaad, M. M., Sayed, S. G. & El-Dakroury, M. M. Securing the future: Real-time intrusion detection in IIoT smart grids through innovative AI solutions. J. Cybersecur. Inf. Manag. 15(2), 208 (2025).
  2. Qureshi, S. et al. An Adaptive multi-layer architecture for IoT-based IDPS for attacks using deep learning method. Int. J. Netw. Secur. 24(5), 815–827 (2022).
  3. Padmapriya, V. & Srivenkatesh, M. iot network-based cyber attack mitigation in digital twin with multi-level key management using enhanced KNN Model. Int. J. Intell. Syst. Appl. Eng. 12(14s), 49–62 (2024).

Metadata

Authors
Alotaibi, S. S., & Alghamdi, T. A.
Affiliations
Umm al-Qura University (SA)
Corresponding author
Alotaibi, Saud S.
Venue
Scientific Reports
Published
2025-08-19
Volume
15
Issue
1
Pages
30296-30296
ISSN
2045-2322 (ISSN-L)
OpenAlex
W4413304082
Cited by
2
References
28
Citations by year
2026: 1 · 2025: 1
FWCI
0.84
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
  • Physical Sciences › Computer Science › Information Systems › Internet of Things and AI
  • Physical Sciences › Computer Science › Artificial Intelligence › Artificial Immune Systems Applications
Keywords
intrusion detection, Industrial Internet of Things, cyberattack detection, league championship algorithm, feature selection, stacked sparse autoencoder, Hunger Games Search, hyperparameter optimization, WSN-DS dataset, Internet of Things security

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.

A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

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: Deep learning with leagues championship algorithm based intrusion detection on cybersecurity driven industrial IoT systems. https://app.cochat.ai/papers/10.1038/s41598-025-15464-0
The paper
Alotaibi, S. S., & Alghamdi, T. A. (2025). Deep learning with leagues championship algorithm based intrusion detection on cybersecurity driven industrial IoT systems. Scientific Reports. https://doi.org/10.1038/s41598-025-15464-0

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.