Protection of intellectual property and verifying data authenticity is a long-existing problem. In the presence of multiple generative AI frameworks, a question naturally arises on how can we verify the source of a text/image/sound data sample? One solution is watermarking. However, watermarking should not affect downstream tasks. This calls for a need for imperceptible watermarks.

In our recent work, we provide a novel approach to watermarking high-dimensional data distributions, such that it is cryptographically hard to distinguish between watermarked from unwatermarked data.