A Novel Evaluation Approach to Finding Lightweight Machine Learning Algorithms for Intrusion Detection in Computer Network

Building practical and efficient intrusion detection systems in computer network is important in industrial areas today and machine learning technique provides a set of effective algorithms to detect network intrusion. To find out appropriate algorithms for building such kinds of systems, it is necessary to evaluate various types of machine learning algorithms based on specific criteria. In this paper, they propose a novel evaluation formula which incorporates 6 indexes into their comprehensive measurement, including precision, recall, root mean square error, training time, sample complexity and practicability, in order to find algorithms which have high detection rate, low training time, needless training samples and are easy to use like constructing, understanding and analyzing models.

Resource Details

Provided by:
Academy & Industry Research Collaboration Center