Use of Enhanced Data Mining Technique for Malware Detection

Abstract

Data mining is the process of extracting information from an implicit, unknown information source through classification and learning [1]. Using computer programmes, the similarities and dissimilarities and their patterns are classified and organised automatically to form a data set. This useful information helps in research to obtain better results, which are applicable in many fields such as big data, medical data processing, and other applications. Most of the data classification process depends on the learning process to obtain the data automatically. Using general concept learning, the concept learning task is obtained in the machine learning process. It categorises the instances into positive and negative classes by training the instances and then grouping the information. Using the Boolean valued function, these two classes are obtained [2]. The general format of concept learning deals with more than two classes of instances to obtain information from the training instances. Based on the classified results, the models are selected. Precisely based on the positive and negative instances, the new unknown is compared to those identified and grouped into that respective instance. This kind of learning process is known as supervised learning because the class membership of the instances is known. In unsupervised learning, the training instances don’t know the classes, so the instances are grouped through data analysis [3]. Unsupervised learning is derived from supervised learning to make use of information, and a two-step strategy is followed to obtain the class information [4]. Data mining has also proven a useful tool in cyber security solutions for discovering vulnerabilities and gathering indicators for baselining. In this paper, we discussed the role of data mining in information security, the malware detection process, and an overview of the Minnesota Intrusion Detection System (MINDS), which uses a suite of data mining-based algorithms to address different aspects of cyber security.