Performance Analysis of a CNN-Fuzzy Logic Based Real-time Intrusion Detection for Industrial IoT Systems

Boye Aziboledia Frederick; Onate Egerton Taylor

doi:doi:10.11648/j.iotcc.20251304.13

Research Article |

| Peer-Reviewed

Performance Analysis of a CNN-Fuzzy Logic Based Real-time Intrusion Detection for Industrial IoT Systems

Boye Aziboledia Frederick^*

, Onate Egerton Taylor

Published in Internet of Things and Cloud Computing (Volume 13, Issue 4)

Received: 19 September 2025 Accepted: 5 October 2025 Published: 26 November 2025

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

The Industrial Internet of Things has enhanced automation, real-time monitoring, and predictive decision-making in modern industries. The study explores the mixed research methods (qualitative and quantitative). However, the growing connectivity of industrial IoT systems has exposed them to severe cyber threats such as Ransomware, MitM, and DDoS attacks, which can disrupt critical operations and compromise safety. Conventional Intrusion Detection Systems (IDS) often face limitations in achieving high accuracy, rapid detection, and low latency while minimizing false alarms. This study proposes a CNN-Fuzzy Logic hybrid model for real-time intrusion detection and prevention in industrial IoT environments. Convolutional Neural Networks (CNN) are employed to extract deep hierarchical features from industrial IoT traffic, while fuzzy logic is integrated to enhance decision-making under uncertainty and reduce false positives. The model was trained and evaluated using Kaggle cybersecurity datasets containing ransomware, MitM, and DDoS attacks. Performance evaluation demonstrates that the CNN-Fuzzy IDS achieves an accuracy of 92.5%, a detection rate of approximately 93%, a false positive rate (FPR) of 2.51%, a reduced latency with an average of 7.14% total latency (which corresponds to 1.207 µsec average latency) is very acceptable for most industrial IoT applications. These results highlight the effectiveness of hybrid intelligent systems in enhancing the resilience and reliability of industrial IoT cybersecurity. The proposed model provides a promising pathway for deploying scalable, adaptive, and real-time IDS solutions in critical industrial infrastructures. On system computational overhead researchers should employ a minimum practical setup with modern multi-core CPU, 8–16 GB RAM, SSD, stable OS (Windows 10 only if hardware is modern) or run a lightweight Linux on edge plus offload heavy tasks elsewhere. Future research should also focus on optimizing hybrid ML architectures for low performance metrics for deployment of resource-constrained industrial IoT devices, integrating the approach for threat detection, and expanding evaluation to real-world industrial environments.

Published in	Internet of Things and Cloud Computing (Volume 13, Issue 4)
DOI	10.11648/j.iotcc.20251304.13
Page(s)	94-109
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2025. Published by Science Publishing Group

Keywords

Industrial IoT, Intrusion Detection System (IDS), Convolutional Neural Networks (CNN), Fuzzy Logic, Real-time Cybersecurity, ML Metrics

References

[1]	Sharma, K., Soumya, B., & Brijesh, K. (2022). Intrusion Detection System in IoT Network using ML, Volume 20, Issue 13, Page 3597-3601\| https://doi.org/10.14704/nq.2022.20.13.NQ88441
[2]	Ahmed C. M, Gauthama R. M R, Aditya M. (2021). Challenges in Machine Learning based approaches for Real-Time Anomaly Detection in Industrial Control Systems, ResearchGate.
[3]	Ramya, M. (2022). What Is a Man-in-the-Middle Attack? Definition, Detection, and Prevention Best Practices for 2022, www.spiceworks.com/it-security/data-security/articles/man-in-the-middle-attack/
[4]	H-ISAC, (2021). Distributed Denial of Service (DDoS), Health-ISAC, www.H-isac.org
[5]	Chika, A. (2023). Ransomware - An Overview, https://www.nomoreransom.org
[6]	Lin, P., Lee, Y., & Huang, C. (2015). A Hybrid Machine Learning Approach for Intrusion Detection Using K-NN, Cluster Center, CANN, and SVM. International Journal of Network Security, 17(6), 674–683.
[7]	Aziz, A. S. A. (2016). Comparison of classification techniques applied for network intrusion detection and classification. Journal of Applied Logic 24. Elsevier, 109-118.
[8]	Kayvan A, S. Yahya, Amirali R. & Siti Hazyanti Binti M. H (2016). “Anomaly Detection Based on Profile Signature in Network using Machine Learning Techniques.” Presented at the 2016 IEEE Region 10 Symposium (TENSYMP), pp. 71–76.
[9]	Deyban, P., Miguel, A. A., Perez, A. D. & Eugenio, S. (2017). Intrusion detection in computer networks using hybrid machine learning techniques. XLIII Latin American Computer Conference IEEE, 1-10.
[10]	Vinoth, Y. & Kamatchi, K. (2020). Anomaly Based Network Intrusion Detection using Ensemble Machine Learning Technique. International Journal of Research in Engineering, Science and Management, (290-296).
[11]	Usman S. M. Megha C., Aniso A. & Mandeep K., (2020). Intrusion Detection System using Machine Learning Techniques: A Review, ResearchGate.
[12]	Maniriho et al. (2020). Detecting Intrusions in Computer Network Traffic with Machine Learning Approaches. International Journal of Intelligent Engineering and Systems. INASS. (433-445).
[13]	Guardian Nigeria (2022). Technology, Ransomware hits 71% of Nigerian organisations, guardian.ng/technology/ransomware-hits-71-of-nigerian-organisations/
[14]	Danane, Y. & Parvat, T. (2015). Intrusion detection system using fuzzy genetic algorithm,” in Pervasive Computing (ICPC), 2015 International Conference on. IEEE, 1–5.
[15]	Ramadhan, A. M. A., Wael, M. S. Y., Hashem, A., Ghilan, Al-Madhagy, T. H., Abdel-Hamid, M. E. & Ahmed, A. W. (2022). Ransomware Detection using Machine and Deep Learning Approaches. International Journal of Advanced Computer Science and Applications, 13(11).
[16]	Alsaidi, R. (2021). Ransomware detection dataset (RDD) dataset. Ransomware detection dataset (RDD) dataset. Available: Kaggle, https://www.kaggle.com/ramdhanamalsaidi/a-novel-datasetcontaining-405836-url Accessed November 28, 20.
[17]	Alhawi, M., Baldwin, J. & Dehghantanha, A. (2018). Leveraging machine learning techniques for windows ransomware network traffic detection. Cyber Threat Intelligence, 93- 106.
[18]	Almashhadani, A. O., Kaiiali, M., Sakir S., & Philip O. (2019). A multi-classifier network-based crypto ransomware detection system: A case study of locky ransomware. IEEE Access, 7, 47053-47067.
[19]	Ghanei H., Manavi F. & Hamzeh A. (2021). A novel method for malware detection based on hardware events using deep neural networks. Journal of Computer Virology and Hacking Technology, 17(4), 319–331.
[20]	Almiani, M., AbuGhazleh, B., Al-Rahayfeh, A., Atiewi, S. & Razaque, A. (2020). Deep Recurrent Neural Network for IoT Intrusion Detection System. Science Direct Simulation Model for Practical Theory, 101, 102031.
[21]	Jiang, K., Wang, W., Wang, A. & Wu, H. (2020). Network intrusion detection combined hybrid sampling with deep hierarchical network. IEEE Access, 8(32), 464 – 476.
[22]	Asad, M., Asim, M., Javed, T., Beg, M. O., Mujtaba, H. & Abbas, S. (2020). Deepdetect: detection of distributed denial of service attacks using deep learning. Ae Computer Journal, 63(7), 983–994.
[23]	Susilo, B & Sari, R (2020). Intrusion Detection in IoT Networks Using Deep Learning Algorithm. Information 2020, 11, 279.
[24]	Djaballah, K. A, Boukhalfa, K., Ghalem, Z. & Boukerma, O. (2020). A novel approach for the detection and analysis of phishing in social networks: the case of Twitter. In 2020 Seventh International Conference on Social Networks Analysis, Management and Security.
[25]	Bagaa, M., Taleb, T., Bernal, J. & Skarmeta, A (2020). A machine learning Security Framework for Iot Systems. IEEE Access, 8, 114066–114077.
[26]	Homayoun, S., Dehghantanha, A., Ahmadzadeh, M., Hashemi, S., Khayami, R., Choo, K. K. & Newton, D. E. (2019). DRTHIS: Deep ransomware threat hunting and intelligence system at the fog layer. Future Generation Computer Systems, 94-104.
[27]	Shanmugam, B. & Idris, N. B. (2019). Improved intrusion detection system using fuzzy logic for detecting anomaly and misuse type of attacks. In Proceeding of 2009 International Conference of Soft Computing and Pattern Recognition, 212-217.
[28]	Hamamoto, A. H. Carvalho, L. F. L., Sampaio, D. H., Abrão, T. & Proença, M. L. (2018). Network anomaly detection system using genetic algorithm and fuzzy logic. Expert Systems with Applications, 92, 390-402.
[29]	Davies, I., Taylor, O., Anireh, V., & Bennett, E. (2024). Adaptive Hybrid Case-Based Neuro-Fuzzy Model for Intrusion Detection and Prevention for Smart Home Network.
[30]	Taylor, O. E., Ezekiel, P. S., & Igiri, C. G. (2021). Anomaly based intrusion detection/prevention system using deep reinforcement learning algorithm. Int. Journal of Adv. Research in Computer and Communication Engineering, 10(1), 58-65.
[31]	Boye, A. F., Taylor, E. O. and Bhagat, D., (2024). AI and Performance Capability of Cybersecurity in the Energy Industry. ISAR Journal of Science and Technology, 2(12), 29-36.
[32]	Tseng A, Chen Y, Kao Y & Lin T. (2016). Deep learning for ransomware detection. IEICE Tech. Rep. 116(282), 87-92.
[33]	Ferrag, M. A., Friha, O., Hamouda, D., Maglaras, L., Member, S. & Janicke, H. (2022). Edge-IIoTset: A New Comprehensive Realistic Cyber Security Dataset of IoT and IIoT Applications for Centralized and Federated Learning”. Institute of Electrical and Electronic Engineering TechRxiv conference.
[34]	Boye A. F. and Onate Egerton Taylor (Analysis on Cybersecurity Control and Monitoring Techniques in Industrial IoT: Industrial Control Systems, 2023; 11(1), 1-17 https://doi.org/10.11648/j.iotcc.20231101.11

Cite This Article

Plain Text BibTeX RIS

APA Style

Frederick, B. A., Taylor, O. E. (2025). Performance Analysis of a CNN-Fuzzy Logic Based Real-time Intrusion Detection for Industrial IoT Systems. Internet of Things and Cloud Computing, 13(4), 94-109. https://doi.org/10.11648/j.iotcc.20251304.13

Copy | Download

ACS Style

Frederick, B. A.; Taylor, O. E. Performance Analysis of a CNN-Fuzzy Logic Based Real-time Intrusion Detection for Industrial IoT Systems. Internet Things Cloud Comput. 2025, 13(4), 94-109. doi: 10.11648/j.iotcc.20251304.13

Copy | Download

AMA Style

Frederick BA, Taylor OE. Performance Analysis of a CNN-Fuzzy Logic Based Real-time Intrusion Detection for Industrial IoT Systems. Internet Things Cloud Comput. 2025;13(4):94-109. doi: 10.11648/j.iotcc.20251304.13

Copy | Download

@article{10.11648/j.iotcc.20251304.13,
  author = {Boye Aziboledia Frederick and Onate Egerton Taylor},
  title = {Performance Analysis of a CNN-Fuzzy Logic Based Real-time Intrusion Detection for Industrial IoT Systems
},
  journal = {Internet of Things and Cloud Computing},
  volume = {13},
  number = {4},
  pages = {94-109},
  doi = {10.11648/j.iotcc.20251304.13},
  url = {https://doi.org/10.11648/j.iotcc.20251304.13},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.iotcc.20251304.13},
  abstract = {The Industrial Internet of Things has enhanced automation, real-time monitoring, and predictive decision-making in modern industries. The study explores the mixed research methods (qualitative and quantitative). However, the growing connectivity of industrial IoT systems has exposed them to severe cyber threats such as Ransomware, MitM, and DDoS attacks, which can disrupt critical operations and compromise safety. Conventional Intrusion Detection Systems (IDS) often face limitations in achieving high accuracy, rapid detection, and low latency while minimizing false alarms. This study proposes a CNN-Fuzzy Logic hybrid model for real-time intrusion detection and prevention in industrial IoT environments. Convolutional Neural Networks (CNN) are employed to extract deep hierarchical features from industrial IoT traffic, while fuzzy logic is integrated to enhance decision-making under uncertainty and reduce false positives. The model was trained and evaluated using Kaggle cybersecurity datasets containing ransomware, MitM, and DDoS attacks. Performance evaluation demonstrates that the CNN-Fuzzy IDS achieves an accuracy of 92.5%, a detection rate of approximately 93%, a false positive rate (FPR) of 2.51%, a reduced latency with an average of 7.14% total latency (which corresponds to 1.207 µsec average latency) is very acceptable for most industrial IoT applications. These results highlight the effectiveness of hybrid intelligent systems in enhancing the resilience and reliability of industrial IoT cybersecurity. The proposed model provides a promising pathway for deploying scalable, adaptive, and real-time IDS solutions in critical industrial infrastructures. On system computational overhead researchers should employ a minimum practical setup with modern multi-core CPU, 8–16 GB RAM, SSD, stable OS (Windows 10 only if hardware is modern) or run a lightweight Linux on edge plus offload heavy tasks elsewhere. Future research should also focus on optimizing hybrid ML architectures for low performance metrics for deployment of resource-constrained industrial IoT devices, integrating the approach for threat detection, and expanding evaluation to real-world industrial environments.
},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - Performance Analysis of a CNN-Fuzzy Logic Based Real-time Intrusion Detection for Industrial IoT Systems

AU  - Boye Aziboledia Frederick
AU  - Onate Egerton Taylor
Y1  - 2025/11/26
PY  - 2025
N1  - https://doi.org/10.11648/j.iotcc.20251304.13
DO  - 10.11648/j.iotcc.20251304.13
T2  - Internet of Things and Cloud Computing
JF  - Internet of Things and Cloud Computing
JO  - Internet of Things and Cloud Computing
SP  - 94
EP  - 109
PB  - Science Publishing Group
SN  - 2376-7731
UR  - https://doi.org/10.11648/j.iotcc.20251304.13
AB  - The Industrial Internet of Things has enhanced automation, real-time monitoring, and predictive decision-making in modern industries. The study explores the mixed research methods (qualitative and quantitative). However, the growing connectivity of industrial IoT systems has exposed them to severe cyber threats such as Ransomware, MitM, and DDoS attacks, which can disrupt critical operations and compromise safety. Conventional Intrusion Detection Systems (IDS) often face limitations in achieving high accuracy, rapid detection, and low latency while minimizing false alarms. This study proposes a CNN-Fuzzy Logic hybrid model for real-time intrusion detection and prevention in industrial IoT environments. Convolutional Neural Networks (CNN) are employed to extract deep hierarchical features from industrial IoT traffic, while fuzzy logic is integrated to enhance decision-making under uncertainty and reduce false positives. The model was trained and evaluated using Kaggle cybersecurity datasets containing ransomware, MitM, and DDoS attacks. Performance evaluation demonstrates that the CNN-Fuzzy IDS achieves an accuracy of 92.5%, a detection rate of approximately 93%, a false positive rate (FPR) of 2.51%, a reduced latency with an average of 7.14% total latency (which corresponds to 1.207 µsec average latency) is very acceptable for most industrial IoT applications. These results highlight the effectiveness of hybrid intelligent systems in enhancing the resilience and reliability of industrial IoT cybersecurity. The proposed model provides a promising pathway for deploying scalable, adaptive, and real-time IDS solutions in critical industrial infrastructures. On system computational overhead researchers should employ a minimum practical setup with modern multi-core CPU, 8–16 GB RAM, SSD, stable OS (Windows 10 only if hardware is modern) or run a lightweight Linux on edge plus offload heavy tasks elsewhere. Future research should also focus on optimizing hybrid ML architectures for low performance metrics for deployment of resource-constrained industrial IoT devices, integrating the approach for threat detection, and expanding evaluation to real-world industrial environments.

VL  - 13
IS  - 4
ER  -

Copy | Download

Author Information

Boye Aziboledia Frederick

Department of Computer Science, Rivers State University, Port Harcourt, Nigeria

Contact Email

http://orcid.org/0009-0004-9395-4686
Onate Egerton Taylor

Department of Computer Science, Rivers State University, Port Harcourt, Nigeria

Contact Email

http://orcid.org/0000-0003-4477-9987

Download PDF

Submit an Article

Sections

Plain Text BibTeX RIS

APA Style

Frederick, B. A., Taylor, O. E. (2025). Performance Analysis of a CNN-Fuzzy Logic Based Real-time Intrusion Detection for Industrial IoT Systems. Internet of Things and Cloud Computing, 13(4), 94-109. https://doi.org/10.11648/j.iotcc.20251304.13

Copy | Download

ACS Style

Frederick, B. A.; Taylor, O. E. Performance Analysis of a CNN-Fuzzy Logic Based Real-time Intrusion Detection for Industrial IoT Systems. Internet Things Cloud Comput. 2025, 13(4), 94-109. doi: 10.11648/j.iotcc.20251304.13

Copy | Download

AMA Style

Frederick BA, Taylor OE. Performance Analysis of a CNN-Fuzzy Logic Based Real-time Intrusion Detection for Industrial IoT Systems. Internet Things Cloud Comput. 2025;13(4):94-109. doi: 10.11648/j.iotcc.20251304.13

Copy | Download

@article{10.11648/j.iotcc.20251304.13,
  author = {Boye Aziboledia Frederick and Onate Egerton Taylor},
  title = {Performance Analysis of a CNN-Fuzzy Logic Based Real-time Intrusion Detection for Industrial IoT Systems
},
  journal = {Internet of Things and Cloud Computing},
  volume = {13},
  number = {4},
  pages = {94-109},
  doi = {10.11648/j.iotcc.20251304.13},
  url = {https://doi.org/10.11648/j.iotcc.20251304.13},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.iotcc.20251304.13},
  abstract = {The Industrial Internet of Things has enhanced automation, real-time monitoring, and predictive decision-making in modern industries. The study explores the mixed research methods (qualitative and quantitative). However, the growing connectivity of industrial IoT systems has exposed them to severe cyber threats such as Ransomware, MitM, and DDoS attacks, which can disrupt critical operations and compromise safety. Conventional Intrusion Detection Systems (IDS) often face limitations in achieving high accuracy, rapid detection, and low latency while minimizing false alarms. This study proposes a CNN-Fuzzy Logic hybrid model for real-time intrusion detection and prevention in industrial IoT environments. Convolutional Neural Networks (CNN) are employed to extract deep hierarchical features from industrial IoT traffic, while fuzzy logic is integrated to enhance decision-making under uncertainty and reduce false positives. The model was trained and evaluated using Kaggle cybersecurity datasets containing ransomware, MitM, and DDoS attacks. Performance evaluation demonstrates that the CNN-Fuzzy IDS achieves an accuracy of 92.5%, a detection rate of approximately 93%, a false positive rate (FPR) of 2.51%, a reduced latency with an average of 7.14% total latency (which corresponds to 1.207 µsec average latency) is very acceptable for most industrial IoT applications. These results highlight the effectiveness of hybrid intelligent systems in enhancing the resilience and reliability of industrial IoT cybersecurity. The proposed model provides a promising pathway for deploying scalable, adaptive, and real-time IDS solutions in critical industrial infrastructures. On system computational overhead researchers should employ a minimum practical setup with modern multi-core CPU, 8–16 GB RAM, SSD, stable OS (Windows 10 only if hardware is modern) or run a lightweight Linux on edge plus offload heavy tasks elsewhere. Future research should also focus on optimizing hybrid ML architectures for low performance metrics for deployment of resource-constrained industrial IoT devices, integrating the approach for threat detection, and expanding evaluation to real-world industrial environments.
},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - Performance Analysis of a CNN-Fuzzy Logic Based Real-time Intrusion Detection for Industrial IoT Systems

AU  - Boye Aziboledia Frederick
AU  - Onate Egerton Taylor
Y1  - 2025/11/26
PY  - 2025
N1  - https://doi.org/10.11648/j.iotcc.20251304.13
DO  - 10.11648/j.iotcc.20251304.13
T2  - Internet of Things and Cloud Computing
JF  - Internet of Things and Cloud Computing
JO  - Internet of Things and Cloud Computing
SP  - 94
EP  - 109
PB  - Science Publishing Group
SN  - 2376-7731
UR  - https://doi.org/10.11648/j.iotcc.20251304.13
AB  - The Industrial Internet of Things has enhanced automation, real-time monitoring, and predictive decision-making in modern industries. The study explores the mixed research methods (qualitative and quantitative). However, the growing connectivity of industrial IoT systems has exposed them to severe cyber threats such as Ransomware, MitM, and DDoS attacks, which can disrupt critical operations and compromise safety. Conventional Intrusion Detection Systems (IDS) often face limitations in achieving high accuracy, rapid detection, and low latency while minimizing false alarms. This study proposes a CNN-Fuzzy Logic hybrid model for real-time intrusion detection and prevention in industrial IoT environments. Convolutional Neural Networks (CNN) are employed to extract deep hierarchical features from industrial IoT traffic, while fuzzy logic is integrated to enhance decision-making under uncertainty and reduce false positives. The model was trained and evaluated using Kaggle cybersecurity datasets containing ransomware, MitM, and DDoS attacks. Performance evaluation demonstrates that the CNN-Fuzzy IDS achieves an accuracy of 92.5%, a detection rate of approximately 93%, a false positive rate (FPR) of 2.51%, a reduced latency with an average of 7.14% total latency (which corresponds to 1.207 µsec average latency) is very acceptable for most industrial IoT applications. These results highlight the effectiveness of hybrid intelligent systems in enhancing the resilience and reliability of industrial IoT cybersecurity. The proposed model provides a promising pathway for deploying scalable, adaptive, and real-time IDS solutions in critical industrial infrastructures. On system computational overhead researchers should employ a minimum practical setup with modern multi-core CPU, 8–16 GB RAM, SSD, stable OS (Windows 10 only if hardware is modern) or run a lightweight Linux on edge plus offload heavy tasks elsewhere. Future research should also focus on optimizing hybrid ML architectures for low performance metrics for deployment of resource-constrained industrial IoT devices, integrating the approach for threat detection, and expanding evaluation to real-world industrial environments.

VL  - 13
IS  - 4
ER  -

Copy | Download