Anomaly Detection in Smart IoT Systems Based on Contextual Semantics of Behavior Graphs
Qixiao Lin, Shuyuan Chang, Jian Mao, Qinghua Liu, Ziwen Liu, Yifan Lu, Yan Huo · IEEE Internet of Things Journal · 2024
With the advancement of Internet of Things (IoT) technology, smart IoT systems have become integral to industrial production and daily life. However, they face significant security and privacy vulnerabilities from different aspects. To enhance the security mechanisms, “Meta Computing” techniques (also called “Network-as-a-Computer, NaaC”) integrate all available computing resources and support zero-trust environments. Traditional anomaly detection methods consider the correlation between two events, which can be bypassed by constructing fake events that indirectly influence target devices, leading to false negatives. To address this issue, behavior-context-based approaches struggle with the complexity and variability of behavior patterns, resulting in false positives due to their inability to tolerate slight differences in event sequences representing the same system behavior. In this paper, we propose an anomaly detection approach in smart IoT systems based on the contextual semantics of behavior graphs. Our method captures critical event semantics while tolerating variations in noncritical events to aggregate and summarize the behavior semantics. We cluster benign behaviors and use whether the testing behavior instance falls into the benign behavior clusters as the criterion for anomaly detection. Our experiment results show that our approach effectively differentiates between anomalous and benign behaviors, significantly reducing false positives and negatives compared to state-of-the-art methods.