paperAugust 2026Unreviewed

Attribute-based Undetectable Watermarking for Generative AI Models

Mi-Ying Huang, Chung-Wei Lee, Maximilian Raffel, Eric Tang

Abstract

Generative AI systems increasingly produce content whose provenance is difficult to verify, motivating watermarking techniques for identifying model-generated outputs. Existing cryptographic watermarking methods provide strong undetectability guarantees: without a detection key, watermarked outputs are computationally indistinguishable from unwatermarked ones. However, these approaches do not address the crucial deployment challenge of how to safely delegate detection capabilities. With an unres

Cite

@misc{huang2026attributebased,
  title = {{Attribute-based Undetectable Watermarking for Generative AI Models}},
  author = {Mi-Ying Huang and Chung-Wei Lee and Maximilian Raffel and Eric Tang},
  year = {2026},
  month = aug,
  eprint = {2608.03174},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/22b014d8b34c436dd36d1d6f95c2702661e6c876}
}