LINE

Text:AAAPrint
Sci-tech

Turtle or rifle? Google AI tricked by MIT students

1
2017-11-06 09:59CGTN Editor: Gu Liping ECNS App Download

From facial recognition technology on smartphones to self-driving systems on vehicles, artificial intelligence (AI) has permeated into many areas of human life. But, are these smart systems reliable?

A Massachusetts Institute of Technology (MIT)-based team called Labsix, has fooled Google's AI InceptionV3 image classifier with an "adversarial object" – a 3D-printed turtle identified by the system as a rifle.

"Adversarial objects" can be applied to both 2D pictures and 3D models. By using a specific pattern, they can trick AI systems to make an incorrect recognition.

In a video published by Labsix, a normal 3D-printed turtle was always classified correctly by InceptionV3. However, the system was fooled by the "adversarial" turtle model and misjudged it as a rifle from every angle.

"We do this using a new algorithm for reliably producing adversarial examples that cause targeted misclassification under transformations like blur, rotation, zoom, or translation," the team said on its website on Tuesday.

"Our process works for arbitrary 3D models – not just turtles!" the team added.

Besides the turtle, Labsix also printed a 3D baseball that was identified by InceptionV3 as an espresso at every angle.

The result triggers concerns, especially when it comes to AI programs related to classification. Imagine this, someone can simply trick your smartphone into unlocking or make payments by using adversarial objects.

  

Related news

MorePhoto

Most popular in 24h

MoreTop news

MoreVideo

News
Politics
Business
Society
Culture
Military
Sci-tech
Entertainment
Sports
Odd
Features
Biz
Economy
Travel
Travel News
Travel Types
Events
Food
Hotel
Bar & Club
Architecture
Gallery
Photo
CNS Photo
Video
Video
Learning Chinese
Learn About China
Social Chinese
Business Chinese
Buzz Words
Bilingual
Resources
ECNS Wire
Special Coverage
Infographics
Voices
LINE
Back to top Links | About Us | Jobs | Contact Us | Privacy Policy
Copyright ©1999-2018 Chinanews.com. All rights reserved.
Reproduction in whole or in part without permission is prohibited.