Feature selection for intrusion detection systems
This work addresses the challenge of feature selection for intrusion detection systems, which is incremental as it builds on existing methods to improve detection accuracy for network security experts.
The paper tackled the problem of identifying key network traffic features for intrusion detection by proposing a new feature selection method that handles continuous inputs and discrete targets, resulting in a machine learning system achieving 99.9% accuracy in distinguishing DDoS from benign signals.
In this paper, we analyze existing feature selection methods to identify the key elements of network traffic data that allow intrusion detection. In addition, we propose a new feature selection method that addresses the challenge of considering continuous input features and discrete target values. We show that the proposed method performs well against the benchmark selection methods. We use our findings to develop a highly effective machine learning-based detection systems that achieves 99.9% accuracy in distinguishing between DDoS and benign signals. We believe that our results can be useful to experts who are interested in designing and building automated intrusion detection systems.