STAY SAFE: Check Building Occupancy
Laptop/DesktopMobile Device
In the News

February 24, 2020

Wired

This Technique Uses AI to Fool Other AIs

Artificial intelligence has made big strides recently in understanding language, but it can still suffer from an alarming, and potentially dangerous, kind of algorithmic myopia. Research shows how AI programs that parse and analyze text can be confused and deceived by carefully crafted phrases. A sentence that seems straightforward to you or me may have a strange ability to deceive an AI algorithm.

Read the full story at Wired.


This Technique Uses AI to Fool Other AIs

< Previous
HackUCI’s Record-Breaking Weekend
Next >
Hasso Plattner Institute Opens New Research School Branch at UCI

Media interested in interviewing ICS faculty, students or alumni should contact Matt Miller at (949) 824-1562 or via email at matt.miller@uci.edu.