Sitemap | Impressum
web2.0 Diaspora RSS Vimeo taz A-FsA Song MeetUp Twitter Youtube Tumblr Flickr Wikipedia Bitcoin Facebook Bitmessage Betterplace Tor-Netzwerk https-everywhere
11.11.2016 Gesichtserkennung leicht fälschbar

All it takes to steal your face is a special pair of glasses

Your face is quickly becoming a key to the digital world. Computers, phones, and even online stores are starting to use your face as a password. But new research from Carnegie Mellon University shows that facial recognition software is far from secure.

Researchers showed they could trick AI facial recognition systems into misidentifying faces — making someone caught on camera appear to be someone else, or even unrecognizable as human. With a special pair of eyeglass frames, the team forced commercial-grade facial recognition software into identifying the wrong person with up to 100% success rates.

In a test where researchers built a state-of-the-art facial recognition system, a white male test subject wearing the glasses appeared as actress Milla Jovovich with 87.87% accuracy.

The test wasn’t theoretical — the CMU printed out the glasses on glossy photo paper and wore them in front of a camera in a scenario meant to simulate accessing a building guarded by facial recognition. And they were able to generate glasses that successfully impersonated someone in 100% of tests.

Read more

All articles about

Category[21]: Unsere Themen in der Presse Short-Link to this page:
Link to this page:
Link with Tor: nnksciarbrfsg3ud.onion/de/articles/5802-20161111-gesichtserkennung-leicht-faelschbar.htm
Tags: #Biometrie #Verschluesselung #Smartphone #Handy #Gesichtserkennung #Passwort #faelschbar #Verbraucherdatenschutz #Datenschutz #Datensicherheit #Ergonomie #Datenpannen #Rasterfahndung #ZentraleDatenbanken #Entry-ExitSystem #eBorder #Freizuegigkeit
Created: 2016-11-11 08:50:30
Hits: 896

Leave a Comment

If you like a crypted answer you may copy your
public key into this field. (Optional)
To prevent the use of this form by spam robots, please enter the portrayed character set in the left picture below into the right field.
logos Mitglied im European Civil Liberties Network Creative Commons Bundesfreiwilligendienst We don't store user data World Beyond War Tor - The onion router HTTPS - use encrypted connections We don't use JavaScript For transparency in the civil society