Building Intelligent Automatons with Semantic Reasoning
summary
Claims that graph-based ontologies (stored in a triple store) and a stack of RDF/RDFS/OWL let security teams consolidate alerts, asset, and vuln data into a single knowledge graph that automatically infers missing facts — e.g., if a host has an installed software instance and that release has a CVE, the system infers the host is vulnerable without a scan — and uses Bayes belief networks to trace likely cause‑and‑effect chains, reducing repetitive triage and enabling opportunistic pivoting.
AI-written summary · about
chapters (10)
- 0:00Start
- 3:02WHAT'S THIS ABOUT
- 9:28INFORMATION ARCHITECTURE
- 11:02SEMANTIC TECHNOLOGY
- 13:44HIGH LEVEL STACK
- 22:05WHY USE ONTOLOGY
- 26:48OWL EXAMPLE
- 27:44SEMANTIC REASONING II
- 28:59PRACTICAL EXAMPLE
- 31:07PARTING WORDS
related talks
24mYour company, as a Knowledge Graph - the foundation of cybersecurity’s future
34mIt's Dangerous To SLSA Alone Out There! Take This Artifact Knowledge Graph!
30mCybersecurity Risk Assessment Using LLM Agents and Graph Data Science
35mComplex Querying of Cyber Knowledge Graph for Robust Cyber Defense
21mEnhancing Threat Intelligence Using AI
28mBuilding Smarter Knowledge Graph Pipeline for Secure Semiconductor Chips
26mImproving Cybersecurity Posture with an AI Security Assistant
22mExploring Answer Set Programming for Provenance Graph-Based Cyber Threat Detection: A(…)