Fooling Computer Vision
Podcast: Data SkepticPublished On: Wed Jan 22 2020
Description: 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.
The note was deleted
The note was saved
Your message was sent