arXiv · 2611.21488
Detection-Efficient Watermarking for Vision--Language Agents via Risk-Constrained Strength Allocation
Abstract
Vision--language agents generate descriptions, decisions, and instructions that may be reused by users, downstream agents, and automated workflows, creating a need for provenance mechanisms that support content authenticity and post-deployment auditing without unnecessarily degrading response quality. We present a risk-aware semantic watermarking framework that combines predictive uncertainty with a zero-shot multimodal relevance-risk proxy to allocate watermark strength during decoding. A single risk penalty $λ$ exposes a continuous operating frontier, allowing deployment-time selection of a detection--quality trade-off without model retraining. At a selected operating point, mean watermark strength is reduced by approximately 59.4\% relative to fixed-strength watermarking, while perplexity change falls from 0.3634 to 0.1689 and clean/paraphrased ROC-AUC reaches 0.9552/0.9459. A matched-strength analysis shows that this advantage reflects the allocation policy rather than lower average intervention: at comparable mean strength, risk-constrained allocation achieves substantially higher ROC-AUC than fixed, entropy-only, and criticality-only policies, identifying it as detection-efficient rather than quality-dominant. We further show that threshold calibration on finite samples produces substantial false-positive-rate drift, motivating calibration variance reporting as standard practice for auditable provenance.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Dumindu Samaraweera, Prashant Shekhar. 2026-11-16. Detection-Efficient Watermarking for Vision--Language Agents via Risk-Constrained Strength Allocation. https://searcharxiv.com/abs/2611.21488
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.