Anomaly-based Intrusion Detection and Prevention Using Adaptive Boosting in Software-defined Network
| Autor: | Oliver Samuel Simanjuntak, I Putu Retya Mahendra, Dessyanto Boedi Prasetyo, Rifki Indra Perwira, Yuli Fauziah |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
010302 applied physics
Boosting (machine learning) Computer science 0211 other engineering and technologies Intrusion detection and prevention Denial-of-service attack 02 engineering and technology Intrusion detection system computer.software_genre 01 natural sciences Learning data Server 021105 building & construction 0103 physical sciences Data mining Decision stump Software-defined networking computer |
| Zdroj: | 2019 5th International Conference on Science in Information Technology (ICSITech). |
| Popis: | Anomaly-based intrusion detection and prevention technique is a technology needed in a software-defined network (SDN). The change in the SDN paradigm into a centralized architecture causes one side of weakness, namely vulnerability from denial of service (DoS) attacks. A large amount of data requested from clients to servers in a short time can be used as prediction data using decision stump to produce learning data. Learning data that have been formed will be used to make predictions. This research aims to detect and prevent DoS attacks using an anomaly-based adaptive boosting algorithm. The experimental test results obtained in this paper show that the effectiveness of the adaptive boosting algorithm in detecting attacks reaches 93.3% and can deny access in real-time. The conclusion is that the adaptive boosting algorithm can be used in building the Intrusion detection and prevention system. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|