Understand this story
On November 16, 2026, the Fraunhofer Institute for Secure Information Technology (SIT) demonstrated a deepfake detector designed to identify video callers impersonating others in real time using face swapping and voice cloning. The proof-of-concept system can raise an alert within one second, provide a probability of fraud, and use a heatmap to highlight suspicious imagery. It runs on a local client to protect privacy, but its high computing requirements mean it is not yet suitable for ordinary smartphones. There are currently no other developments supported by factual evidence.
AI-generated from public reports
Latest development · Report
Face Swap and Voice Cloning: How the Fraunhofer SIT Detector Identifies…Developments
1 confirmed developments
- Source:heise online
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 16
heise online
Face Swap and Voice Cloning: How the Fraunhofer SIT Detector Identifies…
Fraunhofer SIT has demonstrated a deepfake detector that can identify video callers disguised in real time using face swapping and voice cloning. The proof of concept can raise an alert within one second, provide a probability of fraud, and mark suspicious areas of the image with a heatmap. It runs locally on the client to protect privacy, but its computational requirements are high, making it unsuitable for ordinary smartphones for now.
AI Trends