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

A Hybrid MAML-reptile Based Few-shot Learning Approach for Securing Fog-iot Networks against Maleficent Behaviors

PDF (1721KB), PP.44-62

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, 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.2026.03.03

Received: 7 Mar. 2025 / Revised: 15 Sep. 2025 / Accepted: 18 Dec. 2025 / Published: 8 Jun. 2026

Index Terms

Security, Fog-IoT Network, Few Shot Learning, MAML-Reptile, GBL, LBL

Abstract

Security in Fog based IoT networks has a major problem where some IoT devices may be compromised due to attacks. This creates vulnerability to the sensitive data flow between Fog and IoT devices. Also, due to heterogeneity in network structure, the probability of attacks in the network is more. To analyze this dynamic and complex structure of fog networks, few shot learning is be a good solution to learn patterns more accurately and identify the maleficent or normal behavior of a device. In deep learning, few shot learning technique is a technique that uses less amount of labeled data for data processing that is more efficient than the traditional deep learning models. In this work, a hybrid MAML (Model Agnostic Meta Learning)-Reptile based few shot learning approach is proposed that secures the fog based IoT infrastructure from variety of attacks by detecting the attacks more accurately. The few shot models considered are Prototypical Networks, Matching Networks, MAML, and Reptile for selection of best model to be run at the fog server for attack detection. The fog node uses the best model to detect the attacks and broadcasts the local behavior list (LBL) to cloud and other fog nodes to generate the global behavior list (GBL) for sharing more attack information to the IoT device layer. Here, we consider standard datasets such as UNSW-NB-15, NSL-KDD, and CICIDS for performing implementations. The performance of the models is analyzed using accuracy, recall, f1-score, precision, inference time, training time, AUC-ROC, cost, energy consumption, and processing latency. From the results, it is observed that the proposed MAML-Reptile hybrid model performs better than other standard models in detecting maleficent behaviors more accurately.

Cite This Paper

Surya Pavan Kumar Gudla, Sourav Kumar Bhoi, Kshira Sagar Sahoo, GNV Rajareddy, "A Hybrid MAML-reptile Based Few-shot Learning Approach for Securing Fog-iot Networks against Maleficent Behaviors", International Journal of Computer Network and Information Security(IJCNIS), Vol.18, No.3, pp. 44-62, 2026. DOI:10.5815/ijcnis.2026.03.03

Reference

[1]Shanhe Yi, Cheng Li, and Qun Li. A survey of fog computing: concepts, applications and issues. In Proceedings of the 2015 workshop on mobile big data, pages 37–42, 2015.
[2]Hany F Atlam, Robert J Walters, and Gary B Wills. Fog computing and the internet of things: A review. big data and cognitive computing, 2(2):10, 2018.
[3]Ivan Stojmenovic, Sheng Wen, Xinyi Huang, and Hao Luan. An overview of fog computing and its security issues. Concurrency and Computation: Practice and Experience, 28(10):2991–3005, 2016.
[4]Flavio Bonomi, Rodolfo Milito, Jiang Zhu, and Sateesh Addepalli. Fog computing and its role in the internet of things. In Proceedings of the first edition of the MCC workshop on Mobile cloud computing, pages 13–16, 2012.
[5]Amir Vahid Dastjerdi, Harshit Gupta, Rodrigo N Calheiros, Soumya K Ghosh, and Rajkumar Buyya. Fog comput ing: Principles, architectures, and applications. In Internet of things, pages 61–75. Elsevier, 2016.
[6]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.
[7]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.
[8]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.
[9]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.
[10]Yifan Wang, Tetsutaro Uehara, and Ryoichi Sasaki. Fog computing: Issues and challenges in security and forensics. In 2015 IEEE 39th annual computer software and applications conference, volume 3, pages 53–59. IEEE, 2015.
[11]Saad Khan, Simon Parkinson, and Yongrui Qin. Fog computing security: a review of current applications and security solutions. Journal of Cloud Computing, 6:1–22, 2017.
[12]Shruti Jadon and Aryan Jadon. An overview of deep learning architectures in few-shot learning domain. arXiv preprint arXiv:2008.06365, 2020.
[13]Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip HS Torr, and Timothy M Hospedales. Learning to compare: Relation network for few-shot learning. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1199–1208, 2018.
[14]Md Moin Uddin Chowdhury, Frederick Hammond, Glenn Konowicz, Chunsheng Xin, Hongyi Wu, and Jiang Li. A few-shot deep learning approach for improved intrusion detection. In 2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON), pages 456–462. IEEE, 2017.
[15]Merna Gamal, Hala M Abbas, Nour Moustafa, Elena Sitnikova, and Rowayda A Sadek. Few-shot learning for discovering anomalous behaviors in edge networks. Computers, Materials and Continua, 69(2):1823–1837, 2021.
[16]MDIslam, Aminu Yusuf, Muhammad Dikko Gambo, and Abdulaziz Y Barnawi. A novel few-shot ml approach for intrusion detection in iot. Arabian Journal for Science and Engineering, pages 1–15, 2024.
[17]Ahmed Samy, Haining Yu, and Hongli Zhang. Fog-based attack detection framework for internet of things using deep learning. Ieee Access, 8:74571–74585, 2020.
[18]Ahmed Demirpolat, Alper Kaan Sarica, and Pelin Angin. Prot´ edge: a few-shot ensemble learning approach to software-defined networking-assisted edge security. Transactions on Emerging Telecommunications Technologies, 32(6):e4138, 2021.
[19]Thin Tharaphe Thein, Yoshiaki Shiraishi, and Masakatu Morii. Few-shot learning-based malicious iot traffic detec tion with prototypical graph neural networks. IEICE TRANSACTIONS on Information and Systems, 106(9):1480 1489, 2023.
[20]Jingcheng Yang, Hongwei Li, Shuo Shao, Futai Zou, and Yue Wu. Fs-ids: A framework for intrusion detection based on few-shot learning. Computers & Security, 122:102899, 2022.
[21]Mostafa Hosseini and Wei Shi. Intrusion detection in iot network using few-shot class incremental learning. In Future of Information and Communication Conference, pages 617–636. Springer, 2024.
[22]Abebe Diro and Naveen Chilamkurti. Leveraging lstm networks for attack detection in fog-to-things communica tions. IEEE Communications Magazine, 56(9):124–130, 2018.
[23]Dina Ayesha S and Siddique AB. Fs3: few-shot and self-supervised framework for efficient intrusion detection in internet of things networks. In Proceedings of the 39th Annual Computer Security Applications Conference, pages 138–149, 2023.
[24]Shizhao Tian, Zhen Wang, Kaiyu Xie, Fansong Chen, and Hongsong Zhu. Fog-enabled intrusion detection method integrating bi-lstm and multi-head self-attention for iot. In 2024 27th International Conference on Computer Sup ported Cooperative Work in Design (CSCWD), pages 2004–2009. IEEE, 2024.
[25]Jake Snell, Kevin Swersky, and Richard Zemel. Prototypical networks for few-shot learning. Advances in neural information processing systems, 30, 2017.
[26]Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Daan Wierstra, et al. Matching networks for one shot learning. Advances in neural information processing systems, 29, 2016.
[27]Rinu Boney and Alexander Ilin. Semi-supervised few-shot learning with maml. 2018.
[28]Uday Kulkarni, Meena SM, Raghavendra Hallyal, Prasanna Sulibhavi, Shankru Guggari, and Akshay R Shanbhag. Optimisation of deep neural network model using reptile meta learning approach. Cognitive Computation and Systems, 2023.
[29]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.
[30]L Dhanabal and SP Shantharajah. A study on nsl-kdd dataset for intrusion detection system based on classification algorithms. International journal of advanced research in computer and communication engineering, 4(6):446–452, 2015.
[31]Ranjit Panigrahi and Samarjeet Borah. A detailed analysis of cicids2017 dataset for designing intrusion detection systems. International Journal of Engineering & Technology, 7(3.24):479–482, 2018.

International Journal of Computer Network and Information Security (IJCNIS)