Menu

Search

  |   Business

Menu

  |   Business

Search

S. Korean research university KAIST unveils deepfake-detecting mobile app

The software, dubbed KaiCatch, detects deepfakes by using AI technology that ascertains abnormal distortions in a subject's face in images.

The Korea Advanced Institute of Science and Technology (KAIST) launched the country's first mobile app that detects deepfakes to curb misinformation and prevent potential harm to those targeted by the technology.

Deepfakes are artificial intelligence (AI) manipulated images or videos.

The software, dubbed KaiCatch, detects deepfakes by using AI technology that ascertains abnormal distortions in a subject's face in images.

For 2,000 won per image uploaded, KaiCatch calculates the likelihood of the image being manipulated.

According to KAIST's Lee Heung-kyu, a professor at the school of computing, he developed image manipulation detection software in 2015, collecting a mass database of images and video data.

Lee added that they would keep updating the software to detect new deepfake technology.

Deepfakes have become a major concern in South Korea as they are used to create porn involving female celebrities.
While KaiCatch is only available on the Android operating system in Korean, the KAIST team would release an iOS version for Apple users and support other languages, including English, Chinese and Japanese.

  • Market Data
Close

Welcome to EconoTimes

Sign up for daily updates for the most important
stories unfolding in the global economy.