Fden: Mining Effective Information of Features in Detecting Network Anomalies
Lists
Only you see this
Abstract
Network anomaly detection is important for detecting and reacting to the presence of network attacks. In this paper, we propose a novel method to effectively leverage the features in detecting network anomalies, named FDEn, consisting of flow-based Feature Derivation (FD) and prior knowledge incorporated Ensemble models (En <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">pk</inf> ). To mine the effective information in features, 149 features are derived to enrich the feature set of the original data with covering more characteristics of network traffic. To leverage these features effectively, an ensemble model En <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">pk</inf> , including CatBoost and XGBoost, based on the bagging strategy is proposed to first detect anomalies by combining numerical features and categorical features. And then, En <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">pk</inf> adjusts the predicted label of specific data by incorporating the prior knowledge of network security. We conduct empirically experiments on the data set provided by the Network Anomaly Detection Challenge (NADC), in which we obtain average improvement up to 61.6%, 31.7%, 50.2%, and 45.0%, in terms of the cost score, precision, recall and F1-score, respectively.
BibTeX
@inproceedings{li2021fden,
author = {Bin Li and Yijie Wang and Mingyu Liu and Kele Xu and Zhongyang Wang and Li Cheng and Yizhou Li},
title = {{Fden: Mining Effective Information of Features in Detecting Network Anomalies}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2021},
doi = {10.1109/icassp39728.2021.9415099},
}Loading related content...