用语义向量实现高容量、实时解码的图像水印，突破256比特限制。
Fast, Secure, and High-Capacity Image Watermarking with Autoencoded Text Vectors
- 将文本消息编码为256维单位向量嵌入图像，实现语义化水印
- 在多个基准上超越最新技术，支持整句信息且解码实时
- 引入统计校准评分，可部署于实际场景，支持溯源与防篡改
现有图像水印系统多聚焦鲁棒性、容量与不可见性，将嵌入内容视为无意义比特，导致容量受限。本文提出LatentSeal，将水印重构为语义通信：轻量级文本自编码器将完整句子映射为256维单位范数潜在向量，通过微调水印模型稳健嵌入，并经秘密可逆旋转加密。系统可隐藏整句信息，实现实时解码，抵御价值度量与几何攻击。在多个基准上，其BLEU-4与精确匹配率优于现有最优方法，突破长期存在的256比特负载上限。同时引入统计校准得分，获得0.97–0.99的ROC AUC，具备实用部署点。通过从比特载荷转向语义潜在向量，LatentSeal实现更鲁棒、高容量、安全且可解释的水印，为出处追溯、篡改说明与可信AI治理提供可行路径。模型、训练与推理代码及数据划分将于发表后公开。
原文摘要 · Abstract (English)
Most image watermarking systems focus on robustness, capacity, and imperceptibility while treating the embedded payload as meaningless bits. This bit-centric view imposes a hard ceiling on capacity and prevents watermarks from carrying useful information. We propose LatentSeal, which reframes watermarking as semantic communication: a lightweight text autoencoder maps full-sentence messages into a compact 256-dimensional unit-norm latent vector, which is robustly embedded by a finetuned watermark model and secured through a secret, invertible rotation. The resulting system hides full-sentence messages, decodes in real time, and survives valuemetric and geometric attacks. It surpasses prior state of the art in BLEU-4 and Exact Match on several benchmarks, while breaking through the long-standing 256-bit payload ceiling. It also introduces a statistically calibrated score that yields a ROC AUC score of 0.97-0.99, and practical operating points for deployment. By shifting from bit payloads to semantic latent vectors, LatentSeal enables watermarking that is not only robust and high-capacity, but also secure and interpretable, providing a concrete path toward provenance, tamper explanation, and trustworthy AI governance. Models, training and inference code, and data splits will be available upon publication.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。