5 papers
Signpost Watermarking: Joint Optimization for Visual Watermark Coexistence
Shruti Agarwal, Vishal Asnani, John Collomosse
We present a method for training imperceptible visual watermarks to coexist with other such watermarks. Recent work has shown that independently trained image watermarking models c…
FlowMark: Mask-Guided Video Watermarking
Vishal Asnani, Shruti Agarwal, John Collomosse
We present FlowMark, a video watermarking framework guided by automatically predicted object masks. In contrast to prior region-based approaches that require user-supplied mask gui…
TokenTrace: Multi-Concept Attribution through Watermarked Token Recovery
Li Zhang, Shruti Agarwal, John Collomosse +2
Generative AI models pose a significant challenge to intellectual property (IP), as they can replicate unique artistic styles and concepts without attribution. While watermarking o…
MAGNET: Augmenting Generative Decoders with Representation Learning and Infilling Capabilities
Savya Khosla, Aditi Tiwari, Kushal Kafle +4
While originally designed for unidirectional generative modeling, decoder-only large language models (LLMs) are increasingly being adapted for bidirectional modeling. However, unid…
On the Coexistence and Ensembling of Watermarks
Aleksandar Petrov, Shruti Agarwal, Philip H. S. Torr +2
Watermarking, the practice of embedding imperceptible information into media such as images, videos, audio, and text, is essential for intellectual property protection, content pro…