AgentMark watermarks agent planning behaviors with multi-bit identifiers via conditional sampling that preserves utility and works on black-box systems.
Improved unbiased watermark for large language models.arXiv preprint arXiv:2502.11268
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CR 3verdicts
UNVERDICTED 3representative citing papers
Adaptive Stealing improves watermark theft efficiency from LLMs via Position-Based Seal Construction and Adaptive Selection modules that dynamically choose optimal attack perspectives.
LLM watermarking adoption is limited by misaligned stakeholder incentives; incentive-aligned approaches such as in-context watermarking can enable practical use in targeted domains like education and peer review.
citing papers explorer
-
AgentMark: Utility-Preserving Behavioral Watermarking for Agents
AgentMark watermarks agent planning behaviors with multi-bit identifiers via conditional sampling that preserves utility and works on black-box systems.
-
Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language Models
Adaptive Stealing improves watermark theft efficiency from LLMs via Position-Based Seal Construction and Adaptive Selection modules that dynamically choose optimal attack perspectives.
-
Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption
LLM watermarking adoption is limited by misaligned stakeholder incentives; incentive-aligned approaches such as in-context watermarking can enable practical use in targeted domains like education and peer review.