
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.
4.4
472472 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.
162 Listeners
1,014 Listeners
591 Listeners
440 Listeners
298 Listeners
323 Listeners
142 Listeners
765 Listeners
265 Listeners
189 Listeners
88 Listeners
372 Listeners
199 Listeners
76 Listeners
441 Listeners