| Paper ID | CHLG-2.3 |
| Paper Title |
AN ACCURACY NETWORK ANOMALY DETECTION METHOD BASED ON ENSEMBLE MODEL |
| Authors |
Fengrui Liu, Xuefei Li, Wei Xiong, Haiyang Jiang, Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, China; Gaogang Xie, Computer Network Information Center, Chinese Academy of Sciences; University of Chinese Academy of Sciences, China |
| Session | CHLG-2: ZYELL - NCTUNetwork Anomaly Detection Challenge |
| Location | Zoom |
| Session Time: | Monday, 07 June, 13:00 - 14:45 |
| Presentation Time: | Monday, 07 June, 13:00 - 14:45 |
| Presentation |
Poster
|
| Topic |
Grand Challenge: ZYELL - NCTUNetwork Anomaly Detection Challenge |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Identifying network anomaly detection is important since they may carry critical information in circumstances such as a burst of intrusions, privacy theft, system damage and fraudulent activities. In recent years, there are many detection methods for network anomalies are proposed, however, a single model always faces the problems of over or under-fitting, high bias and variance. An improved method is to comprehensively use the results of multiple models and then reform the final predictions. This paper introduces an ensemble model, which is a powerful technique to increase accuracy on network anomaly detection. By combining three base models Xgboost, LightGBM and Catboost into one anomaly detector, we successfully detect different DDOS-smurf and Probing activities. This ensemble model is verified on ZYELL-NCTU net traffic, which is a large-scale dataset for read-world network anomaly detection. All code are open source in Github and can be directly run on Colab Jupyter Notebook. |
