Fast, Secure, and High-Capacity Image Watermarking with Autoencoded Text Vectors
This addresses the need for high-capacity, interpretable watermarking for applications like provenance and trustworthy AI governance, representing a significant advance rather than an incremental improvement.
The paper tackles the problem of limited capacity in image watermarking systems by proposing LatentSeal, which embeds full-sentence messages as semantic latent vectors instead of meaningless bits, achieving state-of-the-art results with BLEU-4 and Exact Match improvements on benchmarks and breaking the 256-bit payload ceiling.
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.