Humans versus machines: a deepfake detection faceoff

• Main Authors: Goh Dion Hoe-Lian, Pan, Jonathan, Lee, Chei Sian
• Other Authors: Wee Kim Wee School of Communication and Information
• Format: Article
• Language: English
• Published: 2025
• Subjects: Computer and Information Science; Machine learning models; Deepfake detection
• Online Access: https://hdl.handle.net/10356/181973
• Institution: Nanyang Technological University

Machine learning (ML) models for deepfake detection are important for countering the threat of such videos. However, human detection is also critical because automated approaches may not always be available to people online. This study compares ML models versus humans for deepfake detection. Results surprisingly showed that humans performed better. Implications of our work are discussed.