Surya Pavan Kumar Gudla; Sourav Kumar Bhoi; Kshira Sagar Sahoo; GNV Rajareddy

Securing Fog-assisted IoT: An Adaptable and Efficient Threat Identification Approach

PDF (2011KB), PP.78-93

Views: 0 Downloads: 0

Author(s)

Surya Pavan Kumar Gudla ¹ Sourav Kumar Bhoi ^2,* Kshira Sagar Sahoo ³ GNV Rajareddy ⁴

1. Department of Computer Science and Engineering, NCR- PMEC Berhampur, Faculty of Engineering, Biju Patnaik University of Technology (BPUT), Rourkela, 769015, India

2. Department of Computer Science and Engineering, Parala Maharaja Engineering College (Govt.), Berhampur, 761003, India

3. Department of Computer Science and Engineering, SRM University-AP, Amaravati, 522502, India

4. Department of Chemical and Biological Engineering, University of Saskatchewan, Saskatoon, Canada S7H 5A2

* Corresponding author.

DOI: https://doi.org/10.5815/ijcnis.2026.02.05

Received: 16 Oct. 2025 / Revised: 4 Dec. 2025 / Accepted: 18 Jan. 2026 / Published: 8 Apr. 2026

Index Terms

Security, Fog Computing, IoT, Deep Ensemble Learning, Meta-Learner

Abstract

The increase in cyber attacks leads to significant challenges to the security in Fog based IoT environments. Existing studies have been implementing machine learning (ML), ensemble learning (EL) and deep learning (DL) for security, in this study we opted deep ensemble learning (DEL) for detection of threats in fog based IoT environments. The proposed DEL model is build using Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Gated Re-current Units (GRU) as base models, and it is augmented using a metalearner such as Logistic Regression (LR), Random Forest (RF), AdaBoost, XGBoost, CatBoost, and LightGBM and also with a Voting Classifier (VC) for f inding the best model. In our experimentation, the evaluation is performed with different datasets such as DDoS SDN, NSL-KDD, UNSW-NB-15, and IoTID20. In this work, DEL with RF achieved better performance than other models when performance metrics such as accuracy (Acy), precision (Prn), recall (Rcl), F1-Score (F1-S) and AUC-score are considered. For instance, DEL with RF achieved an Acy of 99.99%, Prn of 100%, Rcl of 99.96%, F1-S of 99.98% and AUC-score of 1.00 on IoTID20 dataset. Afterward, to analyze the network performance of the DEL models at fog, we have considered the metrics such as cost, energy, resource utilization, latency and service time. This work shows that DELmodels can improve the security of fog assisted IoT systems.

Cite This Paper

Surya Pavan Kumar Gudla, Sourav Kumar Bhoi, Kshira Sagar Sahoo, GNV Rajareddy, "Securing Fog-assisted IoT: An Adaptable and Efficient Threat Identification Approach", International Journal of Computer Network and Information Security(IJCNIS), Vol.18, No.2, pp.78-93, 2026. DOI:10.5815/ijcnis.2026.02.05

Reference

[1]Ammar Odeh and Anas Abu Taleb. Ensemble-based deep learning models for enhancing IoT intrusion detection. Applied Sciences, 13(21):11985, 2023.
[2]Surya Pavan Kumar Gudla, Sourav Kumar Bhoi, Soumya Ranjan Nayak, Krishna Kant Singh, Amit Verma, and Ivan Izonin. A deep intelligent attack detection framework for fog-based IoT systems. Computational Intelligence and Neuroscience, 2022(1):6967938, 2022.
[3]SuryaPavanKumarGudla, SouravKumarBhoi,SoumyaRanjanNayak,andAmitVerma. Di-ads: Adeepintelligent distributed denial of service attack detection scheme for fog-based IoT applications. Mathematical Problems in Engineering, 2022(1):3747302, 2022.
[4]G Shruthi, Monica R Mundada, S Supreeth, and Bryan Gardiner. Deep learning-based resource prediction and mutated leader algorithm enabled load balancing in fog computing. International Journal of computer networks and information security, 15(4):84–95, 2023.
[5]Shahnawaz Ahmad, Iman Shakeel, Shabana Mehfuz, and Javed Ahmad. Deep learning models for cloud, edge, fog, and IoT computing paradigms: Survey, recent advances, and future directions. Computer Science Review, 49:100568, 2023.
[6]Dipti Prava Sahu, Biswajit Tripathy, and Leena Samantaray. Optimized intrusion detection system in fog computing environment using automatic termination-based whale optimization with elm. International Journal of Computer Network and Information Security, 16(2):79–91, 2024.
[7]SamaaYTarabay, AbeerTwakol, AhmedSSamrah, andYasserIbrahim. Asecure and efficient cryptography system based on chaotic maps for securing data image in fog computing. International Journal of Computer Network and Information Security, 15(1):64–80, 2023.
[8]Riccardo Lazzarini, Huaglory Tianfield, and Vassilis Charissis. A stacking ensemble of deep learning models for IoT intrusion detection. Knowledge-Based Systems, 279:110941, 2023.
[9]Vikas Tomer and Sachin Sharma. Detecting IoT attacks using an ensemble machine learning model. Future Internet, 14(4):102, 2022.
[10]Vibekananda Dutta, Michał Chora´ s, Marek Pawlicki, and Rafał Kozik. A deep learning ensemble for network anomaly and cyber-attack detection. Sensors, 20(16):4583, 2020.
[11]Fatmah Alanazi, Kamal Jambi, Fathy Eassa, Maher Khemakhem, Abdullah Basuhail, and Khalid Alsubhi. Ensem ble deep learning models for mitigating ddos attack in software-defined network. Intelligent Automation & Soft Computing, 33(2), 2022.
[12]Ammar Mohammed and Rania Kora. A comprehensive review on ensemble deep learning: Opportunities and challenges. Journal of King Saud University-Computer and Information Sciences, 35(2):757–774, 2023.
[13]Muhammad Usama Tanveer, Kashif Munir, Madiha Amjad, Syed Ali Jafar Zaidi, Amine Bermak, and Atiq Ur Rehman. Ensemble-guard IoT: A lightweight ensemble model for real-time attack detection on imbalanced dataset. IEEE Access, 2024.
[14]Ayoob Almotairi, Samer Atawneh, Osama A Khashan, and Nour M Khafajah. Enhancing intrusion detection in IoT networks using machine learning-based feature selection and ensemble models. Systems Science & Control Engineering, 12(1):2321381, 2024.
[15]Veeranna Gatate and Jayashree Agarkhed. Enhancing intrusion detection in wireless sensor networks through deep hybrid network empowered by sc-attention mechanism. Iran Journal of Computer Science, pages 1–12, 2024.
[16]Nurhadi Wijaya, Marselina Endah Hiswati, and Sarah Anjani. Deepidx: sophisticated ids model using the generative adversarial network (gan) algorithm. Iran Journal of Computer Science, 5(3):197–204, 2022.
[17]Shahid Ul Haq and Ash Mohammad Abbas. Siad: a traffic generation-based anomaly detection protocol with state improvement for internet of things using deep learning. Iran Journal of Computer Science, pages 1–15, 2024.
[18]Tamara Al-Shurbaji, Mohammed Anbar, Selvakumar Manickam, Iznan H Hasbullah, Nadia ALfriehate, Basim Ah mad Alabsi, Ahmad Reda Alzighaibi, and Hasan Hashim. Deep learning-based intrusion detection system for detecting IoT botnet attacks: A review. IEEE Access, 2025.
[19]TuanAnhTang,LotfiMhamdi,DesMcLernon,SyedAliRazaZaidi, MounirGhogho,andFadiElMoussa. Deepids: Deep learning approach for intrusion detection in software defined networking. Electronics, 9(9):1533, 2020.
[20]Fazlullah Khan, Mian Ahmad Jan, Ryan Alturki, Mohammad Dahman Alshehri, Syed Tauhidullah Shah, and Ateeq ur Rehman. A secure ensemble learning-based fog-cloud approach for cyberattack detection in iomt. IEEE Trans actions on Industrial Informatics, 19(10):10125–10132, 2023.
[21]MPRamkumar, T Daniya, P Mano Paul, and S Rajakumar. Intrusion detection using optimized ensemble classifica tion in fog computing paradigm. Knowledge-Based Systems, 252:109364, 2022.
[22]Prabhat Kumar, Govind P Gupta, and Rakesh Tripathi. A distributed ensemble design based intrusion detection sys tem using fog computing to protect the internet of things networks. Journal of ambient intelligence and humanized Computing, 12(10):9555–9572, 2021.
[23]Poulmanogo Illy, Georges Kaddoum, Christian Miranda Moreira, Kuljeet Kaur, and Sahil Garg. Securing fog-to things environment using intrusion detection system based on ensemble learning. In 2019 IEEE wireless communi cations and networking conference (WCNC), pages 1–7. IEEE, 2019.
[24]Leo Breiman. Classification and regression trees. Routledge, 2017.
[25]Leo Breiman. Random forests. Machine learning, 45:5–32, 2001.
[26]Yoav Freund and Robert E Schapire. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of computer and system sciences, 55(1):119–139, 1997.
[27]Tianqi Chen and Carlos Guestrin. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pages 785–794, 2016.
[28]Liudmila Prokhorenkova, Gleb Gusev, Aleksandr Vorobev, Anna Veronika Dorogush, and Andrey Gulin. Catboost: unbiased boosting with categorical features. Advances in neural information processing systems, 31, 2018.
[29]Guolin Ke, QiMeng,ThomasFinley, TaifengWang, WeiChen, WeidongMa, QiweiYe, andTie-YanLiu. Lightgbm: Ahighly efficient gradient boosting decision tree. Advances in neural information processing systems, 30, 2017.
[30]Singal Gaurav Mukhopadhyay Debajyoti Ahuja, Nisha. Ddos attack sdn dataset. mendeley Data, V1, 2020.
[31]Kiran Mahesh. Nsl-kdd dataset, 2020. Accessed: 2023-06-26.
[32]Nour Moustafa and Jill Slay. Unsw-nb15: a comprehensive data set for network intrusion detection systems (unsw nb15 network data set). In 2015 military communications and information systems conference (MilCIS), pages 1–6. IEEE, 2015.
[33]Imtiaz Ullah and Qusay H Mahmoud. A scheme for generating a dataset for anomalous activity detection in IoT networks. In Canadian conference on artificial intelligence, pages 508–520. Springer, 2020.

International Journal of Computer Network and Information Security (IJCNIS)