The advent of Internet-of-Things (IoT) technology has ushered in a new era of unprecedented interconnectivity, by transforming our living space into a dynamic ecosystem. The challenging part of this is the security risk it poses on the network. Due to the vulnerabilities that are usually associated with smart devices, integrating them within the smart home ecosystem presents significant concern for the need of preserving data privacy, network traffic classification, and proper management of trusted devices. Various techniques have been employed in the development of Network Intrusion Detection System (NIDS) to safeguard the network against the evolving nature of attack deployed by cyber-criminals. This paper presents an Adaptive Hybrid Case-Based Neuro-Fuzzy System (HCBNFS) technique to the development of a robust and efficient Intrusion Detection and Prevention System (IDPS). The HCBNFS technique deploys the CBR as a detection engine to easily detect already known traffic patterns on the network, while the NFIS was deployed as a tuning factor to the reverse phase of the CBR to further investigate unknown traffic to the detection engines case-base. Five network packet features were selected as input variables to the proposed model. These features are the source IP, destination IP, source port, destination port, and network protocol. The model was trained using the CIC-IoT2022 dataset. For this study, the CIC-IoT2002 and a synthetic dataset were used for both testing and evaluating the performance of the system. The experimental results of the system using the CIC-IoT2022 dataset achieved 99% accuracy rate in intrusion detection, and recorded 99.5% for precision, recall, and F1-Score. The empirical evaluation of the proposed model validates its effectiveness and contributes towards the development of a more robust intrusion detection and prevention system. By enhancing data confidentiality, privacy, and security, the model represents a significant step forward in the safeguarding IoT-based smart home network against cyber-criminals.

Internet-of-Things, Artificial Intelligence, Neuro-Fuzzy Inference System, Case-Based Reasoning, Smart Home, Machine Learning

[1] Ahanger, T. A., Tariq, U., Ibrahim, A., Ullah, I., & Bouteraa, Y. "IoT-Inspired Framework of Intruder Detection for Smart Home Security Systems". Electronics, Vol. 9, Issue.9, pp.1361, 2020.
[2] Alalade, E. D. "Intrusion detection system in smart home network using artificial immune system and extreme learning machine hybrid approach". IEEE, pp.1-2, 2020.
[3] Almseidin, M., Al-Sawwa, J., & Alkasassbeh, M. "Anomaly-based Intrusion Detection System using Fuzzy Logic". In the Proceedings of the 2021 International Conference on Information Technology (ICIT), pp.290-295, 2021.
[4] Alrayes, F. S., Alshuqayran, N., Nour, M. K., Al Duhayyim, M., Mohamed, A., Mohammed, A. A. A., . . . Yaseen, I. "Optimal Fuzzy Logic Enabled Intrusion Detection for Secure IoT-Cloud Environment". CMC-COMPUTERS MATERIALS & CONTINUA, Vol.74, Issue.3, pp.6737-6753, 2023.
[5] Butt, N., Shahid, A., Qureshi, K. N., Haider, S., Ibrahim, A. O., Binzagr, F., & Arshad, N. (2022). "Intelligent Deep Learning for Anomaly-Based Intrusion Detection in IoT Smart Home Networks". Mathematics, Vol.10, Issue.23, pp.4598, 2022.
[6] Farhin, F., Sultana, I., Islam, N., Kaiser, M. S., Rahman, M. S., & Mahmud, M. "Attack detection in internet of things using software defined network and fuzzy neural network". In the Proceedings of the 2020 Joint 9th International Conference on Informatics, Electronics & Vision (ICIEV), pp. 1-6, 2020.
[7] Imtiaz, S. I., Khan, L. A., Almadhor, A. S., Abbas, S., Alsubai, S., Gregus, M., & Jalil, Z. "Efficient Approach for Anomaly Detection in Internet of Things Traffic Using Deep Learning". Wireless Communications & Mobile Computing, pp.1-15, 2020.
[8] Johannesson, P., & Perjons, E. "An Introduction to Design Science" (2nd ed.). Springer: 978-3-030-7813, 2021.
[9] Kponyo, J. J., Agyemang, J. O., & Klogo, G. S. "Detecting End-Point (EP) Man-In-The-Middle (MITM) attack based on ARP analysis: a machine learning approach". International Journal of Communication Networks and Information Security, Vol.12, Issue.3, pp.384-388, 2020.
[10] Marimuthu, D., Rao, G. R. K., Mehbodniya, A., Mohanasundaram, D., Sundaram, C. K., Maria, A. B., & Mani, D. "Mathematically Modified Adaptive Neuro-Fuzzy Inference System for an Intelligent Cyber Security System". SN Computer Science, Vol.4, Issue.5, pp.453, 2023.
[11] Moudni, H., Er-rouidi, M., Mouncif, H., & El Hadadi, B. "Black Hole attack Detection using Fuzzy based Intrusion Detection Systems in MANET". Procedia Computer Science, Issue.151, pp.1176-1181, 2019.
[12] Rajput, P. K., & Sikka, G. Multi?agent Architecture "Approach for Self?healing Systems: Run?time Recovery with Case?based Reasoning". Concurrency and Computation: Practice and Experience, Vol.35, Issue.1, 2023.
[13] Raushan Kashypa."Smart Home Design Using IoT", International Journal of Computer Sciences and Engineering, Vol.8, Issue.1, pp.146-150, 2020.
[14] Richa, M., Sakshi, K., & Shubham, G. "Detecting Various Intrusion Attacks using A Fuzzy Triangular Membership Function". International Research Journal of Engineering and Technology (IRJET), Vol.9, Issue.1, pp.932-944, 2022.
[15] Sajjad, D., Hassan, M., Priscilla, K. D., Zohourian, A., Kelvin, A. T., & Ali, G. A.. "CIC-IoT-Dataset2022 [Dataset]". Kaggle, 2022.
[16] Suhasini, V. and Avinash, Y. "Artificial Intelligence Powering Internet of Things", International Journal of Computer Sciences and Engineering, Vol.7, Issue.6, pp.449-456, 2019.
[17] Tariq, N., Asim, M., Khan, F. A., Baker, T., Khalid, U., & Derhab, A. "A blockchain-based multi-mobile code-driven trust mechanism for detecting internal attacks in internet of things". Sensors, Vol.21, Issue.1, pp.23, 2020.