发表机构
University of Massachusetts Amherst; Georgia Institute of Technology; Dolby Laboratories（马萨诸塞大学阿默斯特分校; 佐治亚理工学院; 杜比实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对图像水印组合的挑战，提出TAILOR框架，通过离线表征、联合配置选择和实时校准，在满足抗攻击、误报率、质量和延迟要求下，实现96.21%的请求满意度和41.02 dB的PSNR。
AI 中文摘要
图像水印通过将可验证的身份信息嵌入图像来支持溯源和归属认证。然而，实际部署必须同时满足抗攻击性、误报率（FPR）、图像质量和延迟等要求。现有的水印方法对不同类别的变换具有鲁棒性，因此组合互补方法可以提供比任何单一水印更广泛的保护。但这种组合具有挑战性，因为额外的片段会增加失真和解码成本，并且必须共享相同的误报率预算。为此，我们提出了TAILOR，一个请求条件化的水印组合框架，包含三个阶段：（1）离线表征：将片段恢复率、失真和运行时间作为嵌入强度的响应曲线进行测量；（2）联合配置选择：将请求编码为基于这些曲线的SMT模型，并求解失真最低的片段、强度、顺序和几何恢复的组合；（3）实时校准：在用户的图像上验证所选配置，并修正未能迁移的预测。在跨越五个场景和20种攻击设置的7,321个不同请求上的实验结果表明，TAILOR实现了96.21%的场景平均请求满意度，平均PSNR为41.02 dB，在鲁棒性上优于现有方法，同时持续获得更好的图像质量。代码可在[此HTTPS URL](此HTTPS URL)获取。
英文摘要
Image watermarking supports provenance and attribution by embedding verifiable identity information into images. Practical deployments, however, must jointly satisfy requirements for attack resistance, false-positive rate (FPR), image quality, and latency. Existing watermarking methods are robust to different classes of transformations, so combining complementary methods can provide broader protection than any single watermark. Such composition is challenging, as additional fragments increase distortion and decoding cost and must share the same FPR budget. Therefore, we propose **TAILOR**, a request-conditioned watermark composition framework with three stages: (1) *offline characterization* measures fragment recovery, distortion, and runtime as response curves over embedding strength; (2) *joint configuration selection* encodes the request as an SMT model over these curves and solves for the lowest-distortion composition of fragments, strengths, order, and geometric recovery; and (3) *live calibration* validates the selected configuration on the user's images and refines predictions that fail to transfer. Experimental results across 7,321 distinct requests spanning five scenarios and 20 attack settings show that **TAILOR** achieves **96.21%** scenario-averaged request satisfaction with a mean PSNR of **41.02 dB**, outperforming existing methods in robustness while achieving consistently better image quality. Code is available at [https://github.com/aaFrostnova/Tailor](https://github.com/aaFrostnova/Tailor).
