It looks like there's only one paper in this tag, so it's history isn't too exciting, but you can still check it out below!
April 2024
Deep visual and audio watermarking for AI video editing forensics
This paper proposes V2A-Mark, a method to embed invisible visual and audio watermarks into videos to enable precise tamper localization and copyright protection. It addresses limitations of current forensic methods like poor generalizability and singular functionality. V2A-Mark combines fragile video steganography with robust watermarking, using temporal alignment and c...
Read More