• Explore
    • Contact Us
  • Faculty
  • Research
    • Research Areas
    • Research Centers
  • Graduate Degrees
    • Computer Science Programs
    • Current Graduate Students
  • Undergraduate Degrees
  • News & Events
    • News
    • Seminar Series
    • Distinguished Lecture Series
    • Research Showcase
  • Apply Now
    • Undergraduate Admissions
    • Graduate Admissions
    • Faculty Candidates

Wired: “This Technique Uses AI to Fool Other AIs” (Sameer Singh quoted)

February 25, 2020

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.

« UCI News: “UCI and Disney Research scientists develop AI-enhanced video compression model” (Stephan Mandt quoted)
Computer Science Team Develops CoronavirusTwitterMap »

Latest news

  • Mohsen Imani Receives DARPA Young Faculty Award September 18, 2023
  • New Findings on CAPTCHAs Attract Worldwide Attention September 13, 2023
  • ICS Summer Academy 2023: An ‘Incredible’ College Experience for High School Students September 12, 2023
  • NPR: “Armed with traffic cones, protesters are immobilizing driverless cars” (CS Ph.D. candidate Ziwen Wan quoted) August 29, 2023
  • Alumni Spotlight: From Cancer to Climate Change, Peter Sadowski Applies Machine Learning to Address Real-World Problems August 28, 2023
  • © 2023 UC Regents
  • Feedback
  • Privacy Policy