Classifying of Intrusion Detection System Configurations Using Machine Learning Techniques

Abstract

The design capability of enhanced IDSs is being sought by the detection community because intrusion detection requirements are different from one environment to another. The design is often based on several main challenges and their development remains a difficult task due to the sophistication of the attacks and the complexity of the environments. This development is mainly based on the configuration management of IDS. This article discusses a collaborative approach to classifying IDS configurations to facilitate the competitive sharing of ideas between researchers and developers in academia and industry and specify down the main research ideas and show where they have had an impact because the manual classification of configurations is considered time consuming, cumbersome and prone to errors. Our intention is to solicit the reuse of solutions and help refine the works of the community.