Machine Learning-Based Approaches for Prevention and Detection of IoT Botnet Attacks: A Comprehensive Review
Keywords:
Internet of Things (IoT), Botnet Attacks, Machine Learning, Deep Learning, Intrusion Detection System (IDS), Distributed Denial of Service (DDoS)Abstract
Significantly, the expansion of the Internet of Things has connected a complex web of devices better than ever before, riveting critical security risks. A trend has emerged that botnet attacks are a major problem in the IoT environment. In particular, Distributed Denial of Service (DDoS) attacks are an acute barrier to the IoT every now and then because of the nature of IoT environments. The traditional security mechanisms, the signature-based methods of detection, have been criticized by some researchers as they fail to recognize attacks based on the new version of novel and dynamic patterns. Thus, machine learning (ML) and deep learning (DL) have gained importance for the detection of both known and unknown threats through behavioral analysis. In this review, an elaborate discussion is presented on different traditional ML and DL strategies in order to prevent and detect IoT botnet attacks and their kinds. This includes both signature-based and anomaly-based, the focus being on the way each technique operates, the dataset upon which it was built, performance criteria, and drawbacks. Special attention is paid to recent advancements in deep neural networks and autoencoders, and hybrid frameworks that involve learning paradigms, concocting higher accuracy in detection. It will then discuss the few public datasets that may alternatively be used, issues with the feature list, consideration of a clear downside and a clear application scenario when it comes to evaluating parameters in the results. Despite numerous significant advancements, several issues linger, including data imbalance, cross-environment generalization, false positive rates, and computational overhead. This paper schedules an open research issue and suggests, implicitly the future direction-with, shorter models, real-time detection systems, and getting the opportunities enhanced IoT security.
References
F. Hussain, S. G. Abbas, I. M. Pires, S. Tanveer, U. U. Fayyaz, N. M. Garcia, G. A. Shah, and F. Shahzad, “A two-fold machine learning approach to prevent and detect IoT botnet attacks,” IEEE Access, vol. 9, pp. 163412–163426, 2021, doi: 10.1109/ACCESS.2021.3131014.
Abbas, Ghulam, et al. "An Enhanced Machine Learning & Deep Learning based Intrusion Detection System for Intelligent Network Security: A Comprehensive Analysis to Avoid Intrusions in Big Data-based IoT Ecosystem." The Asian Bulletin of Big Data Management 6.1 (2026): 26-33.
Anandhi, S. V., et al. "Adaptive Deep Learning based Real-Time Intravenous Drip Monitoring and Alerting System." IETE Journal of Research (2026): 1-10.
Harit, Vibhor, Rajeev Dahiya, and Umang Garg. "An optimized deep learning-based intrusion detection system for IoT botnets using hybrid feature selection." Recent Advances in Computational Methods in Science and Technology. CRC Press, 2026. 318-327.
Wasswa, Hassan. A Deep Learning-Based Approach for Detection and Tracking of IoT Botnet Activities. Diss. UNSW Sydney, 2026.
Ghouri, Muhammad Nadeem, et al. "Next-Gen IoT Security: Deep Learning-Based Detection of RPL Attacks in Mobile Converged Networks." IEEE Open Journal of the Communications Society (2026).
Akram, Amna, et al. "Detection of MITM ARP Spoofing Attack: A Machine Learning-Based Framework." 2026 7th International Conference on Advancements in Computational Sciences (ICACS). IEEE, 2026.
Ghosh, Dhrubajyoti, et al. "Machine Learning Based Bot Detection on X With Temporal and Semantic Feature Integration." IEEE Transactions on Computational Social Systems (2026).
Kumara, Shiva. "A Lightweight Deep Learning Based Classification Models for Non-Human Identity Threat Detection." 2026 IEEE 5th International Conference on AI in Cybersecurity (ICAIC). IEEE, 2026.
Xia, Lin, Yuanhe Chen, and Lin Han. "A deep learning-based IoT malware detection approach for electric vehicle charging stations." Scientific Reports 16.1 (2026): 10607.
Kongngam, Kititach, and Prusayon Nintanavongsa. "Deep Learning-Based Intrusion Detection for IoT Devices Using Energy Anomaly." 2026 18th International Conference on Knowledge and Smart Technology (KST). IEEE, 2026.
Onuorah, Martins Onyekwelu, Yanxia Sun, and Daniel Mashao. "Toward Generalization and Interpretable Deep Learning–based Intrusion Detection System for Heterogeneous Network Environments." IEEE Access (2026).
Čatloch, Dušan, et al. "DDoS Attack Detection Using Machine Learning." 2026 IEEE 24th World Symposium on Applied Machine Intelligence and Informatics (SAMI). IEEE, 2026.
Marrah, Saio Alusine, et al. "Deep Learning-Based Network Intrusion Detection for IoT Using CNN and Transformer Models." (2026).
Pagoti, Sai Akshita Dimpu, Teja Sri Pacharu, and Kamalakanta Sethi. "A Hybrid Reinforcement Learning Based Intrusion Detection And Mitigation System for Encrypted Network Traffic." 2026 18th International Conference on COMmunication Systems and NETworks (COMSNETS). IEEE, 2026.
Ogunseyi, Taiwo Blessing, et al. "Performance Analysis of Explainable Deep Learning-Based Intrusion Detection Systems for IoT Networks: A Systematic Review." Sensors 26.2 (2026): 363.
Vincent, Elvis, and Prabu Jayant. "DefenSys: An Integrated Platform for Malware Detection and Containerized Attack Simulation using Deep Learning."
Faarax, Cabdiraxmaan Cabdinuur, and Gagan Sharma. "Machine Learning–Based IoT Botnet Detection: Techniques, Challenges, and Future Research Directions: A Comprehensive Review." International Journal of Research & Technology 14.1 (2026): 367-382.
Ullah, Saeed, et al. "Comparative analysis of deep learning and traditional methods for IoT botnet detection using a multi-model framework across diverse datasets." Scientific Reports 15.1 (2025): 31072.
Koppula, Manasa, and LMI Leo Joseph. "A real-world dataset “IDSIoT2024” for machine learning/deep learning based cyber attack detection system for IoT architecture." 2025 3rd International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT). IEEE, 2025.
Eren, Kazim Kivanç, et al. "Simple yet powerful: Machine learning-based IoT intrusion system with smart preprocessing and feature generation rivals deep learning." IEEE Access (2025).
Naik, SK Lokesh, et al. "A Deep Learning Based Security Enhancements in Software Defined Networks." 2025 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC). IEEE, 2025.
Almalki, Sultan Saaed. "A Deep Learning-Based Framework for Real-Time Detection of Cybersecurity Threats in IoT Environments." International Journal of Advanced Computer Science & Applications 16.3 (2025).
Gupta, Neha. "Advancements in Botnet Detection: An Extensive Analysis of Machine Learning Techniques." 2025 3rd International Conference on Communication, Security, and Artificial Intelligence (ICCSAI). Vol. 3. IEEE, 2025.
Sharma, Himanshu, Prabhat Kumar, and Kavita Sharma. "Deep Learning based Ensemble Model for Intrusion Detection in IoT Network." 2025 International Conference on Innovations in Intelligent Systems: Advancements in Computing, Communication, and Cybersecurity (ISAC3). IEEE, 2025.
Wakili, Almustapha A., et al. "Advancing Machine Learning Strategies for Power Consumption-Based IoT Botnet Detection." Sensors 25.24 (2025): 7553.
Downloads
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
