Data Skeptic

Fooling Computer Vision

Jan. 22, 2020

Wiebe van Ranst 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.  Their attack targets the popular YOLO2 pre-trained image recognition model, and thus, is likely to be widely applicable.

Podparadise.com neither hosts nor alters podcast files. All content © its respective owners.