← 研踪 PaperTrailarXiv:2611.21488 · v1
Detection-Efficient Watermarking for Vision--Language Agents via Risk-Constrained Strength Allocation
面向视觉语言智能体的检测高效水印:基于风险约束的强度分配
首次提交 2026-11-17 01:56
版本更新 2026-11-17 01:56
雷达观测 2026-11-17 16:10
摘要
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 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.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-17 01:56 · 最新观测版本
Detection-Efficient Watermarking for Vision--Language Agents via Risk-Constrained Strength Allocation
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 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.
查看此版本解读 →查看此版本原文 ↗