Knowledge Graphs in Action: Identifying Sanctions Circumvention in a Complex Global Landscape
summary
Conference claims standard list screening misses evasion and shows a working pipeline that combines Databricks + Neo4j via spark connector, entity resolution from sensing API, Linkurious Enterprise for alerts and visualization, and Neo4j Graph Data Science for analytics. The knowledge graph links internal data and open sanctions lists, runs Cypher alerts and shortest‑path with weighted relationship costs, and produces a sanction risk score. Demo surfaces networks of ~680 sanctioned nodes and an entity with sanction_count 362 and distance_to_sanction 0, proving the approach finds circumvention patterns.
AI-written summary · about
chapters (7)
- 0:00Introduction and presenters
- 0:53Sanctions circumvention challenges
- 6:18Limitations of list-based screening
- 8:06Why knowledge graphs excel
- 14:26Live demo: Alerts and entity resolution
- 19:01Live demo: Graph analytics in Databricks
- 28:29Summary and Q&A
related talks
16mGraph-Powered Compliance: Building Intelligent Regulatory Mapping with AI and Neo4j
34mIt's Dangerous To SLSA Alone Out There! Take This Artifact Knowledge Graph!
35mComplex Querying of Cyber Knowledge Graph for Robust Cyber Defense
24mYour company, as a Knowledge Graph - the foundation of cybersecurity’s future
15mLightning Talk: Future-Proofing Compliance: Leveraging Knowledge Graphs and AI in Cybe...
35mGraphRag in Action: Revolutionizing Fraud Detection Techniques
27mChagu: Graph-Powered LLM Shielding and Anomaly Detection for Secure AI Pipelines
28mBuilding Smarter Knowledge Graph Pipeline for Secure Semiconductor Chips