Detection and analysis of cyber attacks in IoT environments with CICIoT2023 data set

The rapid proliferation of Internet of Things (IoT) technologies has also increased the risk of cyber attacks targeting these systems. IoT devices, which often have limited processing power and security measures, are vulnerable to DDoS attacks and other cyber threats, leading to service disruptions and damage to critical infrastructures. In this study, various machine learning and deep learning algorithms were evaluated using the CICIoT2023 dataset to detect and analyze cyber attacks in IoT environments. Models such as Logistic Regression (LR), Decision Trees (DT), Naive Bayes (NB), K-Nearest Neighbors (KNN), Random Forest (RF), Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost), Artificial Neural Networks (ANN), Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN) were compared in terms of their effectiveness in attack detection. The results indicate that AI and machine learning-based approaches are effective in identifying cyber threats in IoT systems. This study aims to contribute to the development of more robust security mechanisms for IoT environments and serve as a guide for future research.