A Comparative Analysis of Anomaly Detection Methods in IoT Networks: An Experimental Study
Source abstract
Abstract
The growth of the Internet of Things (IoT) and its integration with Industry 4.0 and 5.0 are generating new security challenges. One of the key elements of IoT systems is effective anomaly detection, which identifies abnormal behavior in devices or entire systems. This paper presents a comprehensive overview of existing methods for anomaly detection in IoT networks using machine learning (ML). A detailed analysis of various ML algorithms, both supervised (e.g., Random Forest, Gradient Boosting, SVM) and unsupervised (e.g., Isolation Forest, Autoencoder), was conducted. The results of tests conducted on popular datasets (IoT-23 and CICIoT-2023) were collected and analyzed in detail. The performance of the selected algorithms was evaluated using commonly used metrics (Accuracy, Precision, Recall, F1-score). The experimental results showed that the Random Forest and Autoencoder methods are highly effective in detecting anomalies. The article highlights the importance of appropriate data preprocessing to improve detection accuracy. Furthermore, the limitations of a centralized machine learning approach in the context of distributed IoT networks are discussed. The article also presents potential directions for future research in the field of anomaly detection in the IoT.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Anomaly Detection Techniques and Applications · Network Security and Intrusion Detection · Smart Grid Security and Resilience
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Computer Science, Kazimierz Wielki University, 85-064 Bydgoszcz, Poland
Funding
Kazimierz Wielki University
References (73)
Show source-provided references
1. Wójcicki, K., Biegańska, M., Paliwoda, B., and Górna, J. (2022). Internet of Things in Industry: Research Profiling, Application, Challenges and Opportunities—A Review. Energies, 15.10.3390/en15051806 ↗
2. Krishnan, A., and Taparia, A. (2024, October 21). State of IoT Summer 2024. IoT Analytics, Available online: https://iot-analytics.com/product/state-of-iot-summer-2024/.
3. Internet of Things (IoT) Security: Current Status, Challenges and Countermeasures
4. Internet of Things Challenges and Opportunities
5. Internet of Things (IoT) of Smart Homes: Privacy and Security
6. XAI-IoT: An Explainable AI Framework for Enhancing Anomaly Detection in IoT Systems10.1109/ACCESS.2024.3402446 ↗
7. Dynamic Behavioral Profiling for Anomaly Detection in Software-Defined IoT Networks: A Machine Learning Approach
8. The Internet of Things and AI-based optimization within the Industry 4.0 paradigm
9. Czeczot, G., Rojek, I., and Mikołajewski, D. (2024). Autonomous Threat Response at the Edge Processing Level in the Industrial Internet of Things. Electronics, 13.10.3390/electronics13061161 ↗
10. A Survey of Machine Learning Techniques for Detecting Anomaly in Internet of Things (IoT)
11. Oha, C.V., and Farouk, F.S. (2024, October 21). Research Project Concordia University of Edmonton. Available online: https://era.library.ualberta.ca/items/28700e1c-3afc-4892-b12e-5c229df9e056/view/8435d90b-09c8-4121-9c86-19b86e8a1e14/2021_Spring_MISSM_Oha-et-al.pdf.
12. Dwivedi, D., Bhushan, A., Singh, A., and Singh, S. (2024). Detection of Malicious Network Traffic Attacks Using Support Vector Machine. Advances in Security, Privacy, and Trust in Computing Systems, Springer Nature Switzerland.10.1007/978-3-031-64064-3_5 ↗
13. Tripathi, S.L., Balas, V.E., Mohapatra, S.K., Prakash, K.B., and Nayak, J. (2021). Comparative analysis of various supervised machine learning techniques for diagnosis of COVID-19. Electronic Devices, Circuits, and Systems for Biomedical Applications, Academic Press.
14. Overview of random forest methodology and practical guidance with emphasis on computational biology and bioinformatics10.1002/widm.1072 ↗
15. De Medeiros, K., Hendawi, A., and Alvarez, M. (2023). A Survey of AI-Based Anomaly Detection in IoT and Sensor Networks. Sensors, 23.10.3390/s23031352 ↗
16. IoT anomaly detection methods and applications: A survey10.1016/j.iot.2022.100568 ↗
17. Data Anomaly Detection in the Internet of Things: A Review of Current Trends and Research Challenges
18. Al Samara, M., Bennis, I., Abouaissa, A., and Lorenz, P. (2022). A Survey of Outlier Detection Techniques in IoT: Review and Classification. J. Sens. Actuator Netw., 11.10.3390/jsan11010004 ↗
19. Eltanbouly, S., Bashendy, M., Al Naimi, N., Chkirbene, Z., and Erbad, A. (2020, January 2–5). Machine Learning Techniques for Network Anomaly Detection: A Survey. Proceedings of the 2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT), Doha, Qatar.10.1109/ICIoT48696.2020.9089465 ↗
20. Tyagi, A., Singh, A., Yadav, A., and Mehra, P.S. (2024, January 15–16). A Survey on Artificial Intelligence-Based Cyber Security in IoT Networks. Proceedings of the 2024 2nd International Conference on Device Intelligence, Computing and Communication Technologies (DICCT), Dehradun, India.10.1109/DICCT61038.2024.10533050 ↗
21. Network Intrusion Detection: An IoT and Non-IoT-Related Survey10.1109/ACCESS.2024.3473289 ↗
22. Mosallam, B.E., and Ahmed, S.H. (2023, January 15–16). Exploring Effective Outlier Detection inIoT: A Systematic Survey of Techniques and Applications. Proceedings of the 2023 Intelligent Methods, Systems, and Applications (IMSA), Giza, Egypt.10.1109/IMSA58542.2023.10255071 ↗
23. Machine learning approaches to IoT security: A systematic literature review10.1016/j.iot.2021.100365 ↗
24. El-Sofany, H., El-Seoud, S.A., Karam, O.H., and Bouallegue, B. (2024). Using machine learning algorithms to enhance IoT system security. Sci. Rep., 14.10.1038/s41598-024-62861-y ↗
25. Enhancing trustworthiness among IoT network nodes with ensemble deep learning-based cyberattack detection10.1016/j.eswa.2024.124528 ↗
26. Shi, T., McCann, R.A., Huang, Y., Wang, W., and Kong, J. (2024). Malware Detection for Internet of Things Using One-Class Classification. Sensors, 24.10.3390/s24134122 ↗
27. Leveraging Machine Learning for Cyber-security Resilience in Industry 4.0: Challenges and Future Directions10.1109/ACCESS.2024.3482987 ↗
28. Alrefaei, A., and Ilyas, M. (2024). Using Machine Learning Multiclass Classification Technique to Detect IoT Attacks in Real Time. Sensors, 24.10.3390/s24144516 ↗
29. Anomaly Detection in IoT Sensor Data Using Auto Encoder-Based Unsupervised Learning10.14445/23488549/IJECE-V11I8P116 ↗
30. Bank, D., Koenigstein, N., and Giryes, R. (2020). Autoencoders: A Comprehensive Survey. arXiv.
31. Anomaly Detection for Internet of Things Cyberattacks10.32604/cmc.2022.024496 ↗
32. Rafique, S.H., Abdallah, A., Musa, N.S., and Murugan, T. (2024). Machine Learning and Deep Learning Techniques for Internet of Things Network Anomaly Detection—Current Research Trends. Sensors, 24.10.3390/s24061968 ↗
33. A Comprehensive Survey for IoT Security Datasets: Taxonomy, Classification, and Machine Learning Mechanisms10.1016/j.cose.2023.103283 ↗
34. Garcia, S., Parmisano, A., and Erquiaga, M.J. (2024, October 21). IoT-23: A Labeled Dataset with Malicious and Benign IoT Network Traffic (Version1.0.0) [DataSet]. Zenodo. Available online: http://doi.org/10.5281/zenodo.4743746.
35. Neto, E.C.P., Dadkhah, S., Ferreira, R., Zohourian, A., Lu, R., and Ghorbani, A.A. (2023). CICIoT2023: A Real-Time Dataset and Benchmark for Large-Scale Attacks in IoT Environment. Sensors, 23.10.20944/preprints202305.0443.v1 ↗
36. Securing the Internet of Things: Evaluating Machine Learning Algorithms for Detecting IoT Cyberattacks Using CIC-IoT2023 Dataset
37. Maran, P., Yap, T.T.V., Chin, J.-J., Ng, H., Goh, V.T., and Kuek, T.-Y. (2022, January 20–22). Comparison of Machine Learning Models for IoT Malware Classification. Proceedings of the 2022 International Conference on Information Technology and Computer Applications (ICITCA), Bali, Indonesia.10.2991/978-94-6463-094-7_3 ↗
38. A Review on Evaluation Metrics for Data Classification Evaluations10.5121/ijdkp.2015.5201 ↗
39. Louppe, G. (2014). Understanding Random Forests: From Theory to Practice. arXiv.
40. Cutler, A., Cutler, D., and Stevens, J. (2011). Random Forests. The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer. [2nd ed.].10.1007/978-1-4419-9326-7_5 ↗
41. Isolation-Based Anomaly Detection10.1145/2133360.2133363 ↗
42. Luo, T., and Nagarajany, S. (2018). Distributed Anomaly Detection Using Autoencoder Neural Networks in WSN for IoT. 2018 IEEE International Conference on Communications (ICC), IEEE.10.1109/ICC.2018.8422402 ↗
43. Oyedotun, O., and Aouada, D. (2022). A Closer Look at Autoencoders for Unsupervised Anomaly Detection. 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), IEEE.10.1109/ICASSP43922.2022.9746898 ↗
44. Huang, Y., Liu, J., Xiang, X., Wen, P., Wen, S., Chen, Y., and Zhang, Y. (2024). Malware Identification Method in Industrial Control Systems Based on Opcode2vec and CVAE-GAN. Sensors, 24.10.3390/s24175518 ↗
45. Kumari, P., Mangat, V., and Singh, A. (2023, January 6–8). Comparative Analysis of State-of-the-Art Attack Detection Models. Proceedings of the 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), Delhi, India.10.1109/ICCCNT56998.2023.10306428 ↗
46. The Top Ten Artificial Intelligence—Deep Neural Networks for IoT Intrusion Detection System10.1007/s11277-023-10198-6 ↗
47. Deep IoT: A Deep Learning Model for Anomaly and Botnet Detection in IoTNetworks
48. A Comparative Analysis of Machine Learning Techniques for IoT Intrusion Detection. In Foundations and Practice of Security. FPS 2021
49. Association for Computing Machinery (2024). Comparison of Multiple Feature Selection Techniques for Machine Learning-Based Detection of IoT Attacks. Proceedings of the 19th International Conference on Availability, Reliability and Security (ARES ‘24), DL. Article 157.
50. Narayan, K.G., Mookherji, S., Odelu, V., Prasath, R.R., Turlapaty, A., and Das, A.K. (2023). IIDS: Design of Intelligent Intrusion Detection System for Internet-of-Things Applications. arXiv.10.1109/CICT59886.2023.10455720 ↗
51. Singh, B., Kaunert, C., and Gautam, R. (2024). Harnessing Machine Learning Intelligence Against Cyber Threats: Navigating Legal and Ethical Challenges in Global Cyber Investigations. Empowering Entrepreneurial Mindsets with AI, IGI Global.10.4018/979-8-3693-7658-4.ch016 ↗
52. Two-step Data Clustering for Improved Intrusion Detection System Using CICIoT2023 Dataset10.1016/j.prime.2024.100673 ↗
53. Golestani Najafabadi, S., and Makaroff, D. (2024). Exploring Unsupervised One-Class Classifiers for Lightweight Intrusion Detection in IoT Systems. 2024 IEEE International Conference on Distributed Computing Systems (ICDCS), IEEE.10.1109/DCOSS-IoT61029.2024.00042 ↗
54. Manufacturing strategy 4.0: A framework to user towards industry 4.0 implementation for digital transformation10.1108/IMDS-12-2021-0790 ↗
55. Collaborations for Digital Transformation: Case Studies of Industry 4.0 in Brazil10.1109/TEM.2021.3061396 ↗
56. A Review of Deep Learning-Based Anomaly Detection Strategies in Industry 4.0 Focused on Application Fields, Sensing Equipment, and Algorithms10.1109/ACCESS.2024.3424488 ↗
57. Real-time AIoT anomaly detection for industrial diesel generator based an efficient deep learning CNN-LSTM in industry4.010.1016/j.iot.2024.101280 ↗
58. Modern approach to sustainable production in the context of Industry 4.0
59. Development of a flexible data management system, to implement predictive maintenance in the Industry 4.0 context10.1080/00207543.2023.2217293 ↗
60. Rojek, I., Mikołajewski, D., Dostatni, E., and Kopowski, J. (2023). Specificity of 3D Printing and AI-Based Optimization of Medical Devices Using the Example of a Group of Exoskeletons. Appl. Sci., 13.10.3390/app13021060 ↗
61. Neural networks as performance improvement models in intelligent CAPP systems
62. Predictive maintenance in Industry 4.0: A survey of planning models and machine learning techniques10.7717/peerj-cs.2016 ↗
63. Fernando, X., and Lăzăroiu, G. (2024). Energy-Efficient Industrial Internet of Things in Green 6G Networks. Appl. Sci., 14.10.3390/app14188558 ↗
64. Integrating human-centric automation and sustainability through the NAToRM framework: A neuromorphic computing approach for resilient industry 5.0 supply chains
65. Alenezi, A.M., Alsmairat, M.A.K., and Ljepava, N. (2024). Integrating the Triple Pillar: AI Marketing’s Pathway to Enhancing Industry 5.0 Through Sustainability, Resilience, and Customer Engagement. 2024 2nd International Conference on Cyber Resilience (ICCR), IEEE.10.1109/ICCR61006.2024.10533067 ↗
66. Odeh, A., and Abu Taleb, A. (2023). Ensemble-Based Deep Learning Models for Enhancing IoT Intrusion Detection. Appl. Sci., 13.10.3390/app132111985 ↗
67. Damilos, S., Saliakas, S., Karasavvas, D., and Koumoulos, E.P. (2024). An Overview of Tools and Challenges for Safety Evaluation and Exposure Assessment in Industry 4.0. Appl. Sci., 14.10.3390/app14104207 ↗
68. Paul, B., and Rao, M. (2023). Zero-Trust Model for Smart Manufacturing Industry. Appl. Sci., 13.10.3390/app13010221 ↗
69. Raimundo, R.J., and Rosário, A.T. (2022). Cybersecurity in the Internet of Things in Industrial Management. Appl. Sci., 12.10.3390/app12031598 ↗
70. Enhancing Cyberattack Detection Using Dimensionality Reduction with Hybrid Deep Learning on Internet of Things Environment10.1109/ACCESS.2024.3411612 ↗
71. Kuthe, M., Parhad, R., Kindarle, R., Agrawal, P., Gupta, G.K., and Kaur, G. (2024). Securing the internet of things: Safeguarding connectivity in the cyber age. Recent Trends in Mathematics, Statistics, and Engineering: Selected Proceedings of theI CRTMSE2023, AIP Publishing.10.1063/5.0234478 ↗
72. A framework to connect IoT edge networks through 3D Massive MIMO10.1007/s11276-023-03512-4 ↗
73. Untangling IoT Global Connectivity: The Importance of Mobile Signaling Traffic10.1109/TNSM.2024.3414975 ↗