The Statistical Analytical Review of IoT Threat Detection Mechanisms: Quantitative Evaluation and Multidimensional Performance Assessment Analysis
DOI:
https://doi.org/10.4108/eetiot.10529Keywords:
IoT Security, Threat Detection, Machine Learning, Performance Evaluation, Internet of Things (IoT), ProcessAbstract
Increased deployment of IoT systems in industrial, healthcare, smart city, and home environments has expanded the attack surface and complexity of cyber threats. Though a plethora of detection techniques have emerged in literature in the last decade, an unforgivable absence of statistical rigors and compare-and-contrast analysis on the operational characteristics is apparent in the literature sets. This paper presents a statistical analytical review of various contemporary IoT threat detection methods across a wide array of architectures: classical machine learning, deep learning, federated learning, blockchain-based systems, quantum-enhanced frameworks, and hybrid models. The review employs a multidimensional evaluation strategy, extracting both qualitative and quantitative metrics from each study; these enable an objective comparison across heterogeneous systems, Standard performance parameters—Scalability, Delay, Time Complexity, Memory Complexity, Make span, and Analysis Efficiency—are tabulated; thus, an unfolding of a universal analytical framework with almost 300 data points exposes trade-offs, bottlenecks to efficiency, and constraints to deployment. Furthermore, evaluation of the application-specific techniques for healthcare, agriculture, and smart grids were conducted in relation to adaptability and domain specifications. The work identifies that hybrid deep networks (e.g., CNN-LSTM) provide better accuracy at higher computation cost, while TinyML and ensemble models present a trade-off factor for both detection accuracy versus hardware efficiency. In addition, whereas quantum and blockchain Integrated systems have shown to be solid in theory, they face practical impairments. Research gaps identified here lead the discussion on future directions, toward explainability, energy-aware design, and adversarial resilience, thus providing a tangible roadmap toward the next generation of secure IoT frameworks.
Downloads
References
[1] Touqir A, Iradat F, Iqbal W, Rakib A, Taskin N, Jadidbonab H, Haas O. Systematic exploration of fuzzing in IoT: techniques, vulnerabilities, and open challenges: A. Touqir et al. The Journal of Supercomputing. 2025 May 23;81(8):877
[2] Sheeba SM, Shaji RS. Hybrid-CID: Securing IoT with mongoose optimization. International Journal of Computational Intelligence Systems. 2025 Dec;18(1):1-8.
[3] Nandhini S, Rajeswari A, Shanker NR. Cyber-attack detection in IOT-WSN devices with threat intelligence using hidden and connected layer-based architectures. Journal of Cloud Computing. 2024 Dec 20;13(1):159.
[4] Gwassi OAH, Uçan ON, Navarro EA. Cyber-XAI-Block: an end-to-end cyber threat detection and FL-based risk assessment framework for IoT-enabled smart organizations using XAI and blockchain technologies. Multimed Tools Appl. 2024. doi:10.1007/s11042-024-20059-4.
[5] Ranpara R, Patel SK, Kumar OP, Al-Zahrani FA. A computational framework for IoT security integrating deep learning-based semantic algorithms for real-time threat response. Sci Rep. 2025;15(1). doi:10.1038/s41598-025-93898-2.
[6] Singh NJ, Singh KR, Hoque N, Bhattacharyya DK. Massive IoT network traffic analysis using ML and DL methods: an empirical evaluation. J Supercomput. 2025;81(10). doi:10.1007/s11227-025-07575-2.
[7] Mujlid HM, Alshahrani R. Quantum-driven security evolution in IoT: AI-powered cryptography and anomaly detection. J Supercomput. 2025;81(9). doi:10.1007/s11227-025-07582-3.
[8] Nazir A, He J, Zhu N, Wajahat A, Ullah F, Qureshi S, et al. Empirical evaluation of ensemble learning and hybrid CNN-LSTM for IoT threat detection on heterogeneous datasets. J Supercomput. 2025;81(6). doi:10.1007/s11227-025-07255-1.
[9] Batta P, Ahuja S, Kumar A. Future directions for secure IoT frameworks: insights from blockchain-based solutions. Wirel Pers Commun. 2024;139(3):1749–1781. doi:10.1007/s11277-024-11694-z.
[10] Abdullah MA, Yu Y, Cai J, Addo D, Bankas EK, Gu YH, et al. Deep learning IoT malware analysis: investigation and understanding. Neural Comput Appl. 2025;37(21):16941–16968. doi:10.1007/s00521-025-11365-5.
[11] Deswal S. Enhancing IoT gateway management security: a deep learning-based framework for intrusion detection and threat mitigation. Int J Inf Technol. 2025;17(6):3695–3705. doi:10.1007/s41870-025-02441-z.
[12] El Haddouti S, Lazraq W. TinyML strategies for privacy-preserving and cyber threat multi-classification in edge IoT networks. Computing. 2025;107(8). doi:10.1007/s00607-025-01522-y.
[13] Saranya K, Valarmathi A. A multilayer deep autoencoder approach for cross-layer IoT attack detection. Sci Rep. 2025;15(1). doi:10.1038/s41598-025-93473-9.
[14] Pathak M, Mishra KN, Singh SP. Securing data and preserving privacy in cloud IoT-based technologies. Artif Intell Rev. 2024;57(10). doi:10.1007/s10462-024-10908-x.
[15] Sowjanya Y, Gopalakrishnan S, Kumar RD. Elevating IoT healthcare security using ProSRN and ICOM methodologies. Int J Inf Technol. 2025. doi:10.1007/s41870-024-02395-8.
[16] Kuku O, Chrysikos A, Salekzamankhani S. Preparing IoT-enabled organisations for digital forensics: a model for readiness and resilience. Int J Inf Secur. 2025;24(4). doi:10.1007/s10207-025-01079-z.
[17] Alzahrani AIA. Exploring AI and quantum computing synergies in holographic counterpart frameworks for IoT security. J Supercomput. 2025;81(11). doi:10.1007/s11227-025-07682-0.
[18] Dahiya P, Kumar V. Optimized multi-kernel extreme learning machine for authentication threat detection in IoT. Wirel Pers Commun. 2024;139(3):1451–1475. doi:10.1007/s11277-024-11669-0.
[19] Kwala AK, Kant S, Mishra A. Comparative analysis of lattice-based cryptographic schemes for secure IoT communications. Discov Internet Things. 2024;4(1). doi:10.1007/s43926-024-00069-2.
[20] Desikan J, Singh SK, Jayanthiladevi A. BACHAAV: ML-augmented human–AI and cryptographic architecture for IoT threat detection. Int J Inf Technol. 2025. doi:10.1007/s41870-025-02650-6.
[21] Nandanwar H, Katarya R. Optimized intrusion detection and secure data management using GAO-XGBoost and ECC blockchain. Knowl Inf Syst. 2025. doi:10.1007/s10115-025-02513-3.
[22] Tyagi H, Kumar R, Pandey SK. Trust evaluation and prediction using deep learning during blackhole attacks in IoT. Arab J Sci Eng. 2025. doi:10.1007/s13369-025-10256-0.
[23] Ullah S, Wu J, Kamal MM, Saudagar AKJ. KronNet: a lightweight Kronecker-enhanced neural network for IoT intrusion detection. Sci Rep. 2025;15(1). doi:10.1038/s41598-025-08921-3.
[24] Khalique A, Siddiqui F, Ahad MA, Hussain I. Lightweight authentication for IoT devices in sustainable smart cities. Sci Rep. 2025;15(1).
[25] Cook S, Mehrnezhad M, Toreini E. Bluetooth security analysis of health IoT devices: the case of FemTech. Int J Inf Secur. 2024;23(6):3547–3567. doi:10.1007/s10207-024-00883-3.
[26] Nawaz M, Tahira S, Shah D, Ali S, Tahir M. Lightweight ML framework for DDoS detection in IoT networks. Sci Rep. 2025;15(1). doi:10.1038/s41598-025-10092-0.
[27] Kumar A, Kavisankar L, Venkatesan S, Kumar M, Yadav S, Shukla SK, et al. IoT device security audit tools: a layered architecture approach. Int J Inf Secur. 2024;24(1). doi:10.1007/s10207-024-00930-z.
[28] Verreydt S, Van Landuyt D, Joosen W. Run-time threat models for continuous risk assessment. Softw Syst Model. 2024. doi:10.1007/s10270-024-01242-5.
[29] Jablaoui R, Liouane N. Combined CNN–RNN based IoT intrusion detection system. Peer Peer Netw Appl. 2025;18(3). doi:10.1007/s12083-025-01944-7.
[30] Gharbi I, Belaoued M, Derhab A, Barkaoui K. IoT ransomware prediction using machine learning: a survey. SN Comput Sci. 2025;6(3). doi:10.1007/s42979-025-03765-0.
[31] Pawar PP, Femy FF, Rajkumar N, Jeevitha S, Bhuvanesh A, Kumar D. Blockchain-enabled cybersecurity for IoT using elliptic curve cryptography. Int J Inf Technol. 2025. doi:10.1007/s41870-025-02576-z.
[32] Kamatchi K, Uma E. Privacy-preserving federated learning for insider threats in IoT. J Supercomput. 2024;81(1). doi:10.1007/s11227-024-06752-z.
[33] Adam Sahib RB, Bhavani R. IoT-based smart healthcare using efficient data analysis. Peer Peer Netw Appl. 2024;18(1). doi:10.1007/s12083-024-01823-7.
[34] Sinha P, Sahu D, Prakash S, Yang T, Rathore RS, Pandey VK. Hybrid LSTM–CNN secure architecture for IoT. Sci Rep. 2025;15(1). doi:10.1038/s41598-025-94500-5.
[35] McDermott CD, Nicho M. Threat detection in smart homes using a sociotechnical conversational approach. Int J Inf Secur. 2025;24(4). doi:10.1007/s10207-025-01051-x.
[36] AR S, Katiravan J. Anomaly detection in IoT using deep neural networks and blockchain. Sci Rep. 2025;15(1). doi:10.1038/s41598-025-04164-4.
[37] Thilakarathne NN, Bakar MSA, Abas PE, Yassin H. Cyber threat intelligence platform for smart agriculture. Sci Rep. 2025;15(1). doi:10.1038/s41598-025-85320-8.
[38] Indra G, Nirmala E, Nirmala G, Senthilvel PG. Ensemble learning for intrusion detection in smart cities. Peer Peer Netw Appl. 2024;17(6):4230–4246. doi:10.1007/s12083-024-01776-x.
[39] Rezaei H, Taheri R, Jordanov I, Shojafar M. Federated RNN for IoT intrusion detection under adversarial attacks. J Netw Syst Manag. 2025;33(4). doi:10.1007/s10922-025-09963-8.
[40] Almobaideen W, Abu Alghanam O, Abdullah M, Hussain SB, Alam U. Review of ML and DL techniques for malware detection in IoT. Int J Inf Secur. 2025;24(3). doi:10.1007/s10207-025-01027-x.
[41] Mohamed N. A comprehensive framework for cyber threat detection using AI and NLP. Int J Inf Technol. 2025.
[42] Kharoubi K, Cherbal S, Mechta D, Gawanmeh A. CNN-based network intrusion detection for IoT. Cluster Comput. 2025;28(4). doi:10.1007/s10586-024-04904-7.
[43] Jameil AK, Al-Raweshidy H. Quantum-enhanced digital twin IoT for healthcare offloading. Discov Appl Sci. 2025;7(6). doi:10.1007/s42452-025-07101-2.
[44] Amador A, Alsubai S, Kryvinska N, Al Hejaili A, Bouallegue B, Ayari M, et al. Transfer learning with XAI for IoT security. Sci Rep. 2025;15(1). doi:10.1038/s41598-025-12404-w.
[45] Zhang B, Shi R, Li X, Zhang M. Decentralized identifiers for trusted IoT data collection. Sci Rep. 2025;15(1). doi:10.1038/s41598-025-89589-7.
[46] Yang E, Jeong S, Seo C. Feature pruning with deep learning for IoT DDoS detection. Sci Rep. 2025;15(1). doi:10.1038/s41598-025-02152-2.
[47] Alqahtany SS, Shaikh A, Alqazzaz A. EGWO and random forest-based intrusion detection for IoT. Sci Rep. 2025;15(1). doi:10.1038/s41598-024-81147-x.
[48] Alkhabbas F, Munir H, Spalazzese R, Davidsson P. Quality characteristics in IoT systems: an industry case study. Discov Internet Things. 2025;5(1). doi:10.1007/s43926-025-00094-9.
[49] Xiong J, Shen L, Liu Y, Fang X. Quantum-resistant hybrid encryption for smart grid IoT. Sci Rep. 2025;15(1). doi:10.1038/s41598-024-84427-8.
[50] Omkari DY, Shaik K. An integrated two-layered voting framework for coronary artery disease prediction using machine learning. IEEE Access. 2024; 12:56275–56290. doi:10.1109/ACCESS.2024.3389707.
[51] Venkatrao K, Kareemulla S. HDLNET: a hybrid deep learning network for chronic kidney disease detection. IEEE Access. 2023; 11:99638–99652. doi:10.1109/ACCESS.2023.3312183.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Lanka Kavitha, Kareemulla Shaik
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
