Feature selection for intrusion detection systems

Abstract

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.

An efficient intrusion detection systems in fog computing using forward selection and BiLSTM

“…FS is crucial in intrusion detection systems, as it enhances the performance of models by focusing on the most informative features [25]. This improves efficiency, increases accuracy, reduces overfitting, and strengthens the detection and classification of intrusive activities in IoT environments [26], [27].…”

Deep learning: Applications, architectures, models, tools, and frameworks: A comprehensive survey

“…proposed a method based on DBN to gain a good covariance kernel for the Gaussian process. They revealed the good accomplishment of the suggested approach both in regression and classification [32]. In another study, a new convolutional DBNs algorithm was proposed to enhance DBN's capability in extracting the features of high‐dimensional images [33].…”

Nested ensemble selection: An effective hybrid feature selection method

“…Feature selection is key component in data science and machine learning applications in multiple fields including gene expression [4] , intrusion detection [25] , internet of things [35] , and others. Given its importance, there exist many algorithms for feature selection in the literature.…”