
Sign up to save your podcasts
Or


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.
By Kyle Polich4.4
475475 ratings
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.

290 Listeners

622 Listeners

584 Listeners

301 Listeners

333 Listeners

228 Listeners

206 Listeners

203 Listeners

306 Listeners

96 Listeners

519 Listeners

261 Listeners

132 Listeners

228 Listeners

617 Listeners