<?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/338bdb8a956843a68ff2f220a1daf329&quot; frameborder=&quot;0&quot; width=&quot;1356&quot; height=&quot;1017&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1017</height><width>1356</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1017</thumbnail_height><thumbnail_width>1356</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/338bdb8a956843a68ff2f220a1daf329-37447ac017c15c79.gif</thumbnail_url><duration>117.1407</duration><title>Exploring Adversarial Attacks in AI</title><description>In this video, I discuss a real-world scenario involving adversarial attacks on AI-generated prescriptions in a hospital setting. I built a demo to illustrate how an attacker could manipulate a prescription, potentially leading to dire consequences. I hope this example helps you understand the risks involved with AI in healthcare. Please take a look at the demo and let me know your thoughts!</description></oembed>