Towards Real-Time Warning and Defense Strategy AI Planning for Cyber Security Systems Aided by Security Ontology

Cyber security systems generally have the phenomena of passive defense and low-efficiency early warnings. Aiming at above problems, this study proposes a real-time warning plans an AI strategy for cyber system aided by ontology. First, we design ontology that integrates attack graphs, general purpose domain-specific knowledge bases, on basis, (1) develop ontology-driven method warnings attacks, which supports non-intrusive scanning detection (2) combine artificial intelligence planning bounded rationality to recommend automatically execute strategies in conventional scenarios. A case has been performed, results indicate that: proposed can quickly analyze network traffic data warnings, is highly feasible ability implement autonomously, (3) performs best, with 5.4–11.4% increase effectiveness against state-of-the-art counterparts considering APT29 attack. Overall, holds potential cyberattacks under high computing resource constraints.