A Machine Learning-Based Approach for the Detection of DDoS Attacks on the Internet of Things Using CICDDoS2019 Dataset – PortMap
Hanan Sharif · Lahore Garrison University Research Journal of Computer Science and Information Technology · 2024
In today's technological era, the Internet has become ubiquitous, playing a vital role in our daily lives.With the exponential growth of IoT innovation, millions of interconnected IoT-enabled devices rely oncloud services to communicate over the Internet. However, this rapid development also exposes thesedevices to various threats, with DDoS (Distributed Denial of Service) and DoS (Denial of Service)attacks being particularly potent and destructive. DDoS attacks present a unique challenge as they aretough to detect using conventional intrusion detection frameworks and traditional methodologies.Fortunately, advancements in machine learning have provided a promising solution by enablingaccurate differentiation between DDoS attacks and other forms of data. This study proposes a DDoSdetection model based on machine learning algorithms. We used the most recent and freely availableonline dataset called CICDDoS2019 to conduct this study. Various machine learning-basedtechniques were explored to identify the characteristics associated with accurate classification. Amongthe algorithms tested, AdaBoost and XGBoost demonstrated exceptional performance. A hybridapproach will be incorporated into this model as part of future work, further improving its capabilities.It is worth noting that this model will be continuously updated with new data on DDoS attacks, ensuringits relevance and effectiveness in combating emerging threats. By leveraging machine learningtechniques, this approach enhances the detection of DDoS attacks on Internet of Things networks,safeguarding the integrity and security of connected devices and the overall IoT ecosystem.