Researchers Test Secret Message Embedding in Videos Using AI
SMRTR summary
Researchers at Fudan University developed a new method for hiding secret messages in videos using semantic features, aiming for improved security and distortion resistance during online sharing. Trained on Vggface2 and validated on FFHQ, the method was tested on DeepFake MNIST+ videos. Performance was evaluated using metrics like Bits Per Frame and extraction accuracy under various scenarios, showing promise compared to existing techniques.
SMRTR provides this summary for quick context. The original article belongs to Hacker Noon.
Read the original article