Korean team builds tool that disrupts lip-sync deepfakes using audio
In short
- Researchers at Soongsil University and Chung-Ang University developed the MUTE technology.
- MUTE disrupts lip synchronisation in deepfake videos using audio protection alone, the team says.
- The paper was accepted for presentation at NeurIPS 2026, a leading AI conference.
Why the Good News Desk likes this one
Deepfake videos can make a real person appear to say things they never said. MUTE aims to protect a voice by breaking the lip-sync match before a fake can be made. The work is still at research stage, with a NeurIPS 2026 presentation accepted and no public release mentioned in the source.
From The Korea Times
A joint research team from Soongsil University and Chung-Ang University has developed a technology to disrupt lip synchronization in deepfake videos that use artificial intelligence (AI) to make a person's lip movements match an audio track. Soongsil University said Tuesday that the team, led by professor Choi Dae-sun of its AI Security Center and professor Kwon Jun-seok of Chung-Ang University, developed the technology, dubbed MUTE. According to the team, MUTE is the first technology to disrupt lip synchronization in deepfake videos using audio protection alone. The paper, titled “MUTE:...
