Towards Efficient Machine Learning Method for IoT DDoS Attack Detection
This provides a more accurate model for researchers and implementers in IoT security, though it is incremental as it builds on existing AI techniques.
The paper tackles the problem of detecting DDoS attacks in IoT devices by proposing a hybrid feature selection algorithm combined with XGBoost, achieving an accuracy of 99.993% on the CIC IDS 2017 dataset and a recall of 97.64% on the CIC IoT 2023 dataset.
With the rise in the number of IoT devices and its users, security in IoT has become a big concern to ensure the protection from harmful security attacks. In the recent years, different variants of DDoS attacks have been on the rise in IoT devices. Failure to detect DDoS attacks at the right time can result in financial and reputational loss for victim organizations. These attacks conducted with IoT devices can cause a significant downtime of applications running on the Internet. Although researchers have developed and utilized specialized models using artificial intelligence techniques, these models do not provide the best accuracy as there is always a scope of improvement until 100% accuracy is attained. We propose a hybrid feature selection algorithm that selects only the most useful features and passes those features into an XGBoost model, the results of which are explained using feature importances. Our model attains an accuracy of 99.993% on the CIC IDS 2017 dataset and a recall of 97.64 % on the CIC IoT 2023 dataset. Overall, this research would help researchers and implementers in the field of detecting IoT DDoS attacks by providing a more accurate and comparable model.