University in Bochum: Semantic Watermarks for AI Image Recognition Can Be Easily Manipulated
June 24, 2025
June 24, 2025
BOCHUM, Germany, June 24 (TNSjou) -- The University in Bochum issued the following news release:
* * *
Semantic Watermarks for AI Image Recognition Can Be Easily Manipulated
Watermarks are supposed to help decide whether an image is genuine or not. But the technology can be easily tricked.
*
Images generated by Artificial Intelligence (AI) are often almost indistinguishable from real images to the human eye. Watermarks - visible or . . .
* * *
Semantic Watermarks for AI Image Recognition Can Be Easily Manipulated
Watermarks are supposed to help decide whether an image is genuine or not. But the technology can be easily tricked.
*
Images generated by Artificial Intelligence (AI) are often almost indistinguishable from real images to the human eye. Watermarks - visible or . . .