Real-Time Intrusion Detection in Ubiquitous Networks with a String-Based Approach

摘要

In this paper we introduce the detection details and experimental results of our proposed Service-oriented and User-centric Intrusion Detection System (SUIDS). SUIDS is designed for ubiquitous computing environments like a smart home/office. It adopts a novel auditing mechanism and flexible system architecture to meet the special requirements of ubiquitous networks. Specifically, the paper shows how a string-based method is used in a user profile to represent the user's short-term behavior in due course; and how an appropriate string length and threshold value are determined in order to balance the system's false alarm rate and detection effectiveness. As a result, SUIDS achieve realtime intrusion detection in ubiquitous networks with a lightweight and adaptable detection model.