Smart City Gnosys

Smart city article details

Title	Developing Explainable Intrusion Detection Systems For Internet Of Things
ID_Doc	19455
Authors	Celik A.F.; Saglam B.; Demirci S.
Year	2023
Published	16th International Conference on Information Security and Cryptology, ISCTURKEY 2023 - Proceedings
DOI	http://dx.doi.org/10.1109/ISCTrkiye61151.2023.10336102
Abstract	The Internet of Things (IoT) is a pivotal concept that supports the revolutionizing 5G/6G, smart cities, and industrial internet technologies. Although IoT brings countless opportunities for innovation, it is accompanied with several cybersecurity issues and vulnerabilities, as well. In order to cope with these issues, machine learning (ML) based intrusion detection systems (IDSs) are developed to detect unauthorized actions with high accuracy rates. However, the results of these systems cannot be interpreted by the users and cybersecurity experts, since employing ML techniques in a black-box manner is deficient in explaining which particular decisions are made during the detection processes. Explainable Artificial Intelligence (XAI) is an emerging paradigm providing interpretability on the decisions of ML-based IDSs to overcome these limitations. In this paper, we have developed explainable IDSs (X-IDSs) for IoT networks by combining ML and XAI concepts. We have used Logistic Regression (LR), Random Forest (RF) and Decision Tree (DT) algorithms for attack detection purposes. In order to provide explainability for the decision-making process of IDSs, we have applied LIME and SHAP, two popular XAI methods, on the results of the developed IDSs. The results show that our IDSs outperform the works in the literature in terms of accuracy rate, and they provide both local and global explanations to interpret ML-based decisions. © 2023 IEEE.
Author Keywords	cybersecurity; IDS; IoT; LIME; SHAP; XAI

Similar Articles

Id	Similarity	Authors	Title	Published
33346	0.906	Berhili M.; Chaieb O.; Benabdellah M.	Intrusion Detection Systems In Iot Based On Machine Learning: A State Of The Art	Procedia Computer Science, 251 (2024)
36080	0.903	Ahanger T.A.; Ullah I.; Algamdi S.A.; Tariq U.	Machine Learning-Inspired Intrusion Detection System For Iot: Security Issues And Future Challenges	Computers and Electrical Engineering, 123 (2025)
6991	0.903	Aljohani R.; Bushnag A.; Alessa A.	Ai-Based Intrusion Detection For A Secure Internet Of Things (Iot)	Journal of Network and Systems Management, 32, 3 (2024)
18301	0.9	Muna R.K.; Hossain M.I.; Alam M.G.R.; Hassan M.M.; Ianni M.; Fortino G.	Demystifying Machine Learning Models Of Massive Iot Attack Detection With Explainable Ai For Sustainable And Secure Future Smart Cities	Internet of Things (Netherlands), 24 (2023)
37199	0.894	Al-Ambusaidi M.; Yinjun Z.; Muhammad Y.; Yahya A.	Ml-Ids: An Efficient Ml-Enabled Intrusion Detection System For Securing Iot Networks And Applications	Soft Computing, 28, 2 (2024)
47766	0.893	Plazas Olaya M.K.; Vergara Tejada J.A.; Aedo Cobo J.E.	Securing Microservices-Based Iot Networks: Real-Time Anomaly Detection Using Machine Learning	Journal of Computer Networks and Communications, 2024 (2024)
957	0.893	Houichi M.; Jaidi F.; Bouhoula A.	A Comprehensive Study Of Intrusion Detection Within Internet Of Things-Based Smart Cities: Synthesis, Analysis And A Novel Approach	2023 International Wireless Communications and Mobile Computing, IWCMC 2023 (2023)
57650	0.892	Hazman C.; Guezzaz A.; Benkirane S.; Azrour M.	Toward An Intrusion Detection Model For Iot-Based Smart Environments	Multimedia Tools and Applications, 83, 22 (2024)
33875	0.889	Alsulami R.; Alqarni B.; Alshomrani R.; Mashat F.; Gazdar T.	Iot Protocol-Enabled Ids Based On Machine Learning	Engineering, Technology and Applied Science Research, 13, 6 (2023)
5365	0.887	Natarajan B.; Bose S.; Maheswaran N.; Logeswari G.; Anitha T.	A Survey: An Effective Utilization Of Machine Learning Algorithms In Iot Based Intrusion Detection System	12th IEEE International Conference on Advanced Computing, ICoAC 2023 (2023)