| Title | IoT DDoS Traffic Detection Using Adaptive Heuristics Assisted With Machine Learning |
| Publication Type | Conference Paper |
| Year of Publication | 2022 |
| Authors | Al Rahbani, Rani, Khalife, Jawad |
| Conference Name | 2022 10th International Symposium on Digital Forensics and Security (ISDFS) |
| Keywords | Adaptation models, DDoS, Decision Tree, denial-of-service attack, feature extraction, heuristics, IoT, machine learning, machine learning algorithms, Network security, Protocols, pubcrawl, resilience, Resiliency, Scalability, Security Heuristics |
| Abstract | DDoS is a major issue in network security and a threat to service providers that renders a service inaccessible for a period of time. The number of Internet of Things (IoT) devices has developed rapidly. Nevertheless, it is proven that security on these devices is frequently disregarded. Many detection methods exist and are mostly focused on Machine Learning. However, the best method has not been defined yet. The aim of this paper is to find the optimal volumetric DDoS attack detection method by first comparing different existing machine learning methods, and second, by building an adaptive lightweight heuristics model relying on few traffic attributes and simple DDoS detection rules. With this new simple model, our goal is to decrease the classification time. Finally, we compare machine learning methods with our adaptive new heuristics method which shows promising results both on the accuracy and performance levels. |
| DOI | 10.1109/ISDFS55398.2022.9800786 |
| Citation Key | al_rahbani_iot_2022 |
IoT DDoS Traffic Detection Using Adaptive Heuristics Assisted With Machine Learning