Deepfake Detection Accuracy Falls 49% in a Year of AI Video Progress
SMRTR summary
Deepfake detection tools built just a year ago are now failing badly against today's AI-generated videos. A Ukraine-led study found detection accuracy dropped 49%, with older tools struggling against modern generators like Alibaba's Wan 2.2, Hunyuan Video, and Kling, leaving a major gap in digital security.
SMRTR provides this summary for quick context. The original article belongs to Unite AI.
Read the original article