U.S. Army researchers developed a deepfake detection method that will allow for the creation of state-of-the-art soldier technology to support mission-essential tasks such as adversarial threat detection and recognition. The team developed a lightweight, low training complexity and high-performance face biometrics technique that meets the size, weight and power requirements of devices soldiers will need in combat. The researchers developed an innovative theory and mathematical framework, the Successive Subspace Learning, or SSL, as an innovative neural network architecture.
Source: https://www.helpnetsecurity.com/2021/05/07/defakehop-deepfake-detection-method/