Graph-Powered Compliance: Building Intelligent Regulatory Mapping with AI and Neo4j
summary
Demonstrates a working system that models regulations, controls, assets and evidence in a single Neo4j graph, uses LLMs to extract requirements into machine-readable controls, runs Cypher queries and Graph Data Science algorithms for anomaly detection and graph centrality algorithms to rank impact, and integrates results into CI/CD to block or auto-remediate failing deployments. Claims reduced alert fatigue by prioritizing downstream controls, supports multi-cloud resources and OSCAL integration for framework interoperability, and presents compliance-as-code patterns with Neo4j and automated enforcement.
AI-written summary · about
chapters (9)
- 0:00Introduction to talk
- 4:47Why graph for compliance
- 7:37AI on compliance graph
- 8:42OSCAL integration benefits
- 9:46Compliance as code in CI/CD
- 10:48Multi-cloud compliance coverage
- 12:14Managing alert fatigue
- 13:40Emerging compliance frontiers
- 14:44Key takeaways summary
related talks
32mCybersecurity meets Generative AI: Automating Your Compliance...
11mStreamlining Legislative Compliance with Neo4j
15mLightning Talk: Future-Proofing Compliance: Leveraging Knowledge Graphs and AI in Cybe...
15mGraphRAG-Powered AI Agents: Transforming Corporate Metadata into Intelligent Knowledge
29mKnowledge Graphs in Action: Identifying Sanctions Circumvention in a Complex Global Landscape
01h 26mThinking in Graphs: The Cognitive Foundations of Agentic AI
12mLightning Talk: Revolutionize Security GRC: Leverage AI and LLM for Continuous Control...
35mGraphRag in Action: Revolutionizing Fraud Detection Techniques