| Autor: |
Muhammed Ali Aydin, Zeynep Turgut, Serpil Üstebay |
| Rok vydání: |
2018 |
| Předmět: |
|
| Zdroj: |
2018 International Congress on Big Data, Deep Learning and Fighting Cyber Terrorism (IBIGDELFT). |
| DOI: |
10.1109/ibigdelft.2018.8625318 |
| Popis: |
In this study, an intrusion detection system (IDS) has been proposed to detect malicious in computer networks. The proposed system is studied on the CICIDS2017 dataset, which is the biggest dataset available online. In order to overcome the challenges big data created, it is aimed to determine the effects of the features on the data set and to find the most effective features that can differentiate the data in the most meaningful way. Therefore, recursive feature elimination is performed via random forest and the importance value of the features are calculated. Intrusions are detected with the accuracy of 91% by Deep Multilayer Perceptron (DMLP) structure using the obtained features. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
