<?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/cb6b91c7e55945a7ad4526409e667296&quot; frameborder=&quot;0&quot; width=&quot;906&quot; height=&quot;679&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>679</height><width>906</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>679</thumbnail_height><thumbnail_width>906</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/cb6b91c7e55945a7ad4526409e667296-dd47ebf493d134e4.gif</thumbnail_url><duration>415.486</duration><title>DeepMedia Dataset for Deepfake Detection in Gen AI Imagery 📊</title><description>Hi there! In this video, I walk you through our recent release dataset comprising 3,000 images for benchmarking deepfake detection in generative AI imagery. We&apos;ve analyzed the dataset, achieved close to 96% accuracy with low false positive and negative rates, and created innovative visualizations to enhance understanding. Check it out for insights into the latest in deepfake detection!</description></oembed>