Abstract—Intrusion detection systems (IDSs) attempt to identify attacks by comparing new data to predefined signatures known to be malicious (misuse IDSs) or to a model of normal behavior (anomaly-based IDSs). This paper investigates a new model to more effectively detect anomaly intrusions from masqueraders. Events with different weight values based on historical data generated by Windows operating system are collected to build the normal user profiles as a template. A fuzzy system is applied to evaluate and classify the potential threat level from user new activities in a system. Experimental results show the promising results with a high detection rate of masqueraders and a low false alarm rate.
Index Terms—Anomaly intrusion detection, computer security, fuzzy logic, masquerader detection.
Yingbing Yu is with the Department of Computer Science & Information Technology, Austin Peay State University, Clarksville, TN 37044 USA (e-mail: yuy@apsu.edu).
Cite: Yingbing Yu, "Anomaly Intrusion Detection Based upon Anomalous Events and Soft Computing Technique," International Journal of Machine Learning and Computing vol.5, no. 6, pp. 450-453, 2015.