Hybrid Machine Learning Models for IoT Security
Abstract
The swift growth of the Internet of Things (IoT) brings forth considerable security challenges due to the variety of connected devices and their limited resources. Conventional security strategies are unable to keep pace with evolving cyber threats, rendering the IoT ecosystem susceptible to attacks. This paper introduces a hybrid machine-learning framework aimed at enhancing IoT security. Our method merges supervised and unsupervised techniques to detect both known and unknown (zero-day) threats. This hybrid framework utilizes fuzzy detection along with classification algorithms to recognize malicious activities while reducing false positives. We assess the performance of the model using publicly available IoT datasets and compare it to other Machine Learning (ML) models. The findings reveal notable improvements in precision, accuracy, recall, and response time. These results suggest that the hybrid model establishes a more robust basis for safeguarding the IoT environment against threats.
Keywords:
Hybrid machine learning, IoT security, Anomaly detection, Threat classification, Zero-day attacks, Traffic analysis, Real-time detectionReferences
- [1] Sayeed Anwar, Ujjeisheei Panda, & Hitesh Mohapatra. (2024). Legal and ethical issues in IoT based smart city: data privacy, surveillance, and citizen rights. Journal of computer science engineering and software testing, 10(2), 17–26. https://matjournals.net/engineering/index.php/JOCSES/article/view/617
- [2] Mishra, S. R., & Mohapatra, H. (2024). Enhancing money laundering detection through machine learning: A comparative study of algorithms and feature selection techniques. In AI and blockchain applications in industrial robotics (pp. 300–321). IGI Global. https://www.igi-global.com/chapter/enhancing-money-laundering-detection-through-machine-learning/336091
- [3] Mahesh, B. (2020). Machine learning algorithms-a review. International journal of science and research (IJSR).[internet], 9(1), 381–386. https://www.researchgate.net/profile/Batta-Mahesh/publication/344717762_Machine_Learning_Algorithms_-A_Review/links/5f8b2365299bf1b53e2d243a/Machine-Learning-Algorithms-A-Review.pdf?eid=5082902844932096t
- [4] Madakam, S., Ramaswamy, R., & Tripathi, S. (2015). Internet of things (IoT): A literature review. Journal of computer and communications, 3(5), 164–173. https://www.scirp.org/journal/paperinformation?paperid=56616
- [5] Steinwart, I., & Christmann, A. (2008). Support vector machines. Springer Science & Business Media.
- [6] Fleury, A., Vacher, M., & Noury, N. (2009). SVM-based multimodal classification of activities of daily living in health smart homes: sensors, algorithms, and first experimental results. IEEE transactions on information technology in biomedicine, 14(2), 274–283. https://doi.org/10.1109/TITB.2009.2037317
- [7] Priyadarshini, I. (2024). Anomaly detection of IoT cyberattacks in smart cities using federated learning and split learning. Big data and cognitive computing, 8(3), 21. https://doi.org/10.3390/bdcc8030021
- [8] Mirsky, Y., Doitshman, T., Elovici, Y., & Shabtai, A. (2018). Kitsune: An ensemble of autoencoders for online network intrusion detection. ArXiv Preprint ArXiv:1802.09089.
- [9] Wang, X., Chen, M., Xing, C., & Zhang, T. (2016). Defending DDoS attacks in software-defined networking based on legitimate source and destination IP address database. IEICE transactions on information and systems, 99(4), 850–859. https://search.ieice.org/bin/summary.php?id=e99-d_4_850
- [10] Mirkovic, J., & Reiher, P. (2004). A taxonomy of DDoS attack and DDoS defense mechanisms. ACM sigcomm computer communication review, 34(2), 39–53. https://dl.acm.org/doi/abs/10.1145/997150.997156
Issue 1