TY  - JOUR
T1  - Nesnelerin İnterneti Saldırılarının Tespitinde Makine Öğrenmesi Algoritmalarının Performanslarının Karşılaştırılması
TT  - Comparison of Performances of Machine Learning Algorithms in Detectiıon of Internet of Things Attacks
AU  - Yıltırak, İsa
AU  - Öztürk, Ali
PY  - 2025
DA  - September
Y2  - 2025
DO  - 10.38016/jista.1635809
JF  - Journal of Intelligent Systems: Theory and Applications
JO  - JISTA
PB  - Özer UYGUN
WT  - DergiPark
SN  - 2651-3927
SP  - 130
EP  - 140
VL  - 8
IS  - 2
LA  - tr
AB  - Bu çalışmada IoT cihazlarındaki çeşitli saldırı türleri için farklı makine öğrenmesi algoritmalarının sınıflandırma performansları karşılaştırılmıştır. Bu amaçla kullanılan algoritmalar AdaBoost, CatBoost, XGBoost, Karar Ağaçları, K En Yakın Komşu, Rastgele Orman, Light GBM, Lojistik Regresyon ve Gaussian Naïve Bayes'tir. CICIoT2023 veri seti kullanılarak 33 farklı saldırı tipi ve 7 farklı saldırı grubu için saldırı sınıflandırması yapılmıştır. Deneysel sonuçlara göre, makine öğrenmesi algoritmaları arasında Rastgele Orman (RF), 33 saldırı türünü sınıflandırmada %94,90 doğruluk, %94,90 kesinlik, %94,89 hatırlatma, %94,84 F1 puanı, 7 saldırı grubunu sınıflandırmada %94,33 doğruluk, %94,35 kesinlik, %94,33 hatırlatma, %94,31 F1 puanı ve ikili sınıflandırmada %96,81 doğruluk, %97,15 kesinlik, %96,81 hatırlatma, %96,79 F1 puanı oranını elde etti. RF, 33 saldırı türünü sınıflandırmada en iyi performansı gösterdi.
KW  - Makine Öğrenmesi Algoritmaları
KW  - Nesnelerin İnterneti
KW  - Saldırı Tespiti
KW  - Saldırı Türleri.
N2  - In this study, the classification performances of different machine learning algorithms were compared for various types of attacks in IoT devices. The algorithms used for this purpose are AdaBoost, CatBoost, XGBoost, Decision Trees, K Nearest Neighbour, Random Forest, Light GBM, Logistic Regression and Gaussian Naïve Bayes. By using the CICIoT2023 data set, attack classification was carried out for 33 different attack types and 7 different attack groups. According to the experimental results, among the machine learning algorithms, Random Forest (RF) achieved 94.90% accuracy, 94.90% precision, 94.89% recall, 94.84% F1 score in classifying 33 attack types, 94.33% accuracy, 94.35% precision, 94.33% recall, 94.31% F1 score in classifying 7 attack groups and 96.81% accuracy, 97.15% precision, 96.81% recall, 96.79% F1 score in binary classification. RF performedbest in classifying 33 attack types.
CR  - Abdulkareem, S. A., Foh, C. H., Lee, H., Carrez, F., Moessner, K., 2022. IoT Network Intrusion Detection with Ensemble Learners. International Conference on ICT Convergence, 2022-October, 510-514.
CR  - Bala, B., Behal, S., 2024. A Brief Survey of Data Preprocessing in Machine Learning and Deep Learning Techniques. 8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024- Proceedings, 1755-1762.
CR  - Bozdogan, Z., Kara, R., 2015. Layered model architecture for internet of things. Journeal of Engineering Reearch and Applied Science , 4(1), pp 260-264.
CR  - Elaziz, B., Ommane, Y., Eddabbah, M., Laaziz, Y., 2024. Enhancing Diabetes Detection Through Data Preprocessing: A Comparative Analysis of Machine Learning Algorithms. 1st International Conference on Computing, Internet of Things and Microwave Systems, ICCIMS 2024, pp. 1-6
CR  - Guo, G., 2022. An Intrusion Detection System for the Internet of Things Using Machine Learning Models. 2022 3rd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering, ICBAIE 2022, 332-335.
CR  - Happy, Chhikara, R., Kashyap, N., 2024. A Comparative Analysis of Machine Learning Prediction Algorithms for Detecting IoT Botnet Activities. 2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024., pp. 1-6.
CR  - Kasongo, S., M., 2021.An advanced intrusion detection system for IIoT Based on GA and tree based algorithms’, IEEE Access, 9, pp. 113199–113212
CR  - Kouekam, M., Khennou, F., 2024. Securing the Internet of Things: Exploring Ensemble Learning for Attacks Classification. Proceedings- 2024 5th International Conference on Industrial Engineering and Artificial Intelligence, IEAI 2024, 78-84.
CR  - Kumar, A. G., Rastogi, A., Ranga, V., 2024. Evaluation of Different Machine Learning Classifiers on New IoT Dataset CICIoT2023. 2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024, pp. 1-6.
CR  - Manchala, Y., Nayak, J., Behera, H. S. 2023. Detection of Malicious Traffic in IoMT Environment Using Intelligent XGboost Approach. 2022 OPJU International Technology Conference on Emerging Technologies for Sustainable Development, OTCON 2022., pp. 1-6.
CR  - Mittal, S., Mishra, A. K., Tripathi, V., Singh, P., Pandey, P. 2023. A Comparative Analysis of Supervised Machine Learning Models for Smart Intrusion Detection in IoT Network. 2023 3rd Asian Conference on Innovation in Technology, ASIANCON 2023., pp. 1-6 .
CR  - Neto, E. C. P., Dadkhah, S., Ferreira, R., Zohourian, A., Lu, R., Ghorbani, A. A. 2023. CICIoT2023: A Real-Time Dataset and Benchmark for Large-Scale Attacks in IoT Environment. Sensors, 23(13).
CR  - Rahim, R., Chishti, M. A., Raheem, M. M., 2024. Improving the security of Internet of Things (IoT) using Intrusion Detection System(IDS). 21st International Learning and Technology Conference: Reality and Science Fiction in Education, L and T 2024, 290-295.
CR  - Sadhwani, S., Modi, U. K., Muthalagu, R., Pawar, P. M. 2024. SmartSentry: Cyber Threat Intelligence in Industrial IoT. IEEE Access, 12, 34720-34740.
CR  - Sahu, N., K., Mukherjee, I., 2020. Machine Learning based anomaly detection for Network. Proceedings of the 4th International Conference on Trends in Electronics and Informatics (ICOEI 2020): 15-17, June 2020. IEEE., pp. 787-794, 2020.
CR  - Saif, S., Hossain, M. A., Islam, M. S., 2024. IoT Security Fortification: Enhancing Cyber Threat Detection Through Feature Selection and Advanced Machine Learning. 1st International Conference on Innovative Engineering Sciences and Technological Research, ICIESTR 2024- Proceedings., pp. 1-6.
CR  - Saiyed, M., Al Anbagi, I., 2023. Entropy and Divergence-based DDoS Attack Detection System in IoT Networks. International Conference on Wireless and Mobile Computing, Networking and Communications, 2023-June, 224-230.
CR  - Samdekar, R., Ghosh, S. M., Srinivas, K., 2021. Efficiency enhancement of intrusion detection in iot based on machine learning through bioinspire. Proceedings of the 3rd International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2021, 383-387.
CR  - Satılmış H., Akleylek S., 2021. IoT Güvenliği için Kullanılan Makine Öğrenimi ve Derin Öğrenme Modelleri Üzerine Bir Derleme. Bilişim Teknolojileri Dergisi, 14(4), 457-481.
CR  - Sibai, F. N., Asaduzzaman, A., Sibai, A., 2023. A Comparative Study of Machine Learning Methods for Intrusion Detection. Proceedings- 2023 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023, 184-188.
CR  - Thereza, N., Ramli, K., 2023. Development of Intrusion Detection Models for IoT Networks Utilizing CICIoT2023 Dataset. Proceedings of the 3rd 2023 International Conference on Smart Cities, Automation and Intelligent Computing Systems, ICON-SONICS 2023, 66-72.
CR  - Yemmanuru, P. K., Yeboah, J., Khakata Esther, N. G., 2023. Systematic Literature Review of Machine Learning for IoT Security. Proceedings- 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023, 227-233.
UR  - https://doi.org/10.38016/jista.1635809
L1  - https://dergipark.org.tr/tr/download/article-file/4591600
ER  -