A team from SMU has won a grant to develop a deepfake detection tool called DeepShield. A release said that the project will be “the first multilingual deepfake data set that includes dialectal variants such as Singlish and Korean dialects.” SMU Associate Professor of Computer Science He Shengfeng said that many existing tools do not perform well on Asian languages, accents, or content. Leading the team, he said that they are focused on building something that fits the specific needs of the region.
