Deep learning (DL) based anomaly detection has shown great promise in the field of security due to its remarkable performance in various tasks. However, the issue of poor interpretability in DL models has significantly impeded their deployment in practical security applications. Despite the progress made in existing studies on DL explanations, the majority of them focus on providing local explanations for individual samples, neglecting the global understanding of the model knowledge. Furthermore, most explanations for supervised models fail to apply to anomaly detection due to their different learning mechanisms. In this work, we address the gap in the existing research by proposing GEAD, a novel global explanation for DL-based anomaly detection, to extract high-fidelity rules from DL models. We apply GEAD to two security applications, network intrusion detection and system log anomaly detection, and demonstrate the efficacy with three usages: comparing model knowledge with expert knowledge, identifying knowledge discrepancies between models, and combining model and expert knowledge. We provide several case studies to showcase how GEAD can significantly enhance existing anomaly detection systems. Moreover, we provide a real-world deployment in a SCADA system to showcase the potential in practice. Some important insights are drawn to help the community understand and improve anomaly detection systems in security.
In the power monitoring system, when managers review the operation and maintenance requirements, they lack effective evaluation methods for personnel and equipment, and cannot guarantee the accuracy of authorization. This makes the operation and maintenance process more risks and hidden dangers. For this reason, this paper proposes a security operation and maintenance strategy generation technology and functional design scheme based on personnel operation and equipment status evaluation. Firstly, establish a baseline of safe operation and maintenance operations for operation and maintenance personnel, an operation evaluation model for operation and maintenance personnel, equipment status evaluation standards and algorithm models; then, generate differentiated operations policy based on operations request, establish the dynamic access control relationship between staff account and asset account; finally, the functions of equipment status evaluation, operation evaluation of operation-maintenance personnel, and operation-maintenance strategy generation are designed to realize dynamic authorization based on operation-maintenance requirements, and comprehensively improve the operation- maintenance process of power monitoring system Ability to control personnel and equipment.