Insider Threat Detection using Binary Classification Algorithms

The Insider Threat Detection(ISTD), is commonly referred to as the silent killer of organizations. The impact is greatly felt because it is usually perpetrated by existing staff of the organization. This makes it very difficult to detect or can even go undetected. Several authors have researched into this problem but no best solution has been discovered. This study therefore considers the insider problem as a classification problem. It provides a lay man’s understanding of a typical classification problem as faced in the insider threat detection research scope. It then highlights five (5) commonly used binary classification algorithms, stating their strengths and weaknesses. This work will help researchers determine the appropriate algorithm to consider for the employee dataset available for classification.