Fooling Computer Vision

Data Skeptic

Episode | Podcast

Date: Wed, 22 Jan 2020 18:38:55 +0000

<p class="p1"><span class="s1"><a href="https://twitter.com/wiebevr">Wiebe van Ranst</a> joins us to talk about a project in which specially designed printed images can fool a computer vision system, preventing it from identifying a person.<span class="Apple-converted-space"> </span> Their attack targets the popular YOLO2 pre-trained image recognition model, and thus, is likely to be widely applicable.</span></p>