Fooling Computer Vision episode artwork

EPISODE · Jan 22, 2020 · 25 MIN

Fooling Computer Vision

from Data Skeptic

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.

Episode metadata supplied by the publisher feed · Published Jan 22, 2020

Embed this episode

Ready to play

Fooling Computer Vision

0:00 25:26

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

Frequently Asked Questions

How long is this episode of Data Skeptic?

This episode is 25 minutes long.

When was this Data Skeptic episode published?

This episode was published on January 22, 2020.

Can I download this Data Skeptic episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!