No abstract

Recent studies have highlighted that insider threats are more destructive than external network threats. Despite many research studies on this, the spatial heterogeneity and sample imbalance of input features still limit the effectiveness of existing machine learning-based detection methods. To solve this problem, we proposed a supervised insider threat detection method based on ensemble learning and self-supervised learning. Moreover, we propose an entity representation method based on TF-IDF to improve the detection effect. Experimental results show that the proposed method can effectively detect malicious sessions in CERT4.2 and CERT6.2 datasets, where the AUCs are 99.2% and 95.3% in the best case.

Assessing the survivability of mission critical information systems is essential for combat capability analysis in the cyber warfare environments, and the instantaneous availability of system is one of the key indicators for information systems' survivability evaluation. In response to these problems, this paper formulates a network vehicle weapon system as a series repairable system. Then we investigate the probability of reliability and instantaneous availability under our proposed model. The simulation results show that maintenance ability and improved component repair rate are very important to system's reliability and instantaneous availability .

No abstract