<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/3b26c2a168774c84a70c57394f0edf94&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/3b26c2a168774c84a70c57394f0edf94-d8f3cfb0c65dce4a.gif</thumbnail_url><duration>167.04</duration><title>GraphGuard: Detecting Sanctioned Exporters via Ownership</title><description>This Loom demonstrates GraphGuard, a knowledge graph project that detects sanctioned exporters using ownership relations and logical reasoning. It models core entities including people, companies, sanctions, and ownership links, and uses pre-paid data to flag companies linked to sanctioned individuals. The presenter selects example flagged firms like PhoenixSAS78 and Alpha Hosts to show the underlying ownership graph, where relationships are highlighted with red lines. They also cite specific ownership examples including Atlantic, Inc. being 96 percent owned by Phoenix A78 and another case where Alpha Hosts is owned by the sanctioned individual Ivan Petrov. The Loom concludes by showing how questions like why a company is flagged can be answered based on the graph.</description></oembed>