UnMarker: A Universal Attack on Defensive Watermarking

arXiv:2405.08363v1 Announce Type: new
Abstract: Reports regarding the misuse of $\textit{Generative AI}$ ($\textit{GenAI}$) to create harmful deepfakes are emerging daily. Recently, defensive watermarking, which enables $\textit{GenAI}$ providers to hide fingerprints in their images to later use for deepfake detection, has been on the rise. Yet, its potential has not been fully explored. We present $\textit{UnMarker}$ -- the first practical $\textit{universal}$ attack on defensive watermarking. Unlike existing attacks, $\textit{UnMarker}$ requires no detector feedback, no unrealistic knowledge of the scheme or similar …

arxiv attack cs.cr cs.cv cs.lg daily deepfake deepfake detection deepfakes defensive detection emerging fingerprints genai generative generative ai hide images reports watermarking