A review of recent approaches on wrapper feature selection for intrusion detection

In this paper, we present a review of recent advances in wrapper feature selection techniques for attack detection and classification, applied in intrusion detection area. Due to the quantity of published papers in this area, it is difficult to ascertain the level of current research in wrapper feature selection techniques. Moreover, due to the wide variety of techniques and datasets, is difficult to identify relevant characteristics among them, regard it architecture, performance, advantages and issues. The reported results frequently are shown in heterogeneous way, as there are several metrics to measure the classification quality. From our review, we propose a classification taxonomy of the wrapper feature selection techniques in intrusion detection area, considering design, rationale, technical characteristics and common evaluation metrics. Also we consider a description of the common metrics and a brief discussion about the attack scenarios reported in this review. At the end of this work, we show the coverage of existing research, open challenges and new directions.