ClaimMark: Decoder-Differential Watermarking for Claimed-Key Image Provenance

Multi-user image provenance requires more than watermark detection: a verifier must determine whether the evidence supports a submitted key. We introduce ClaimMark, a training-free watermarking method for reference-assisted key attribution. ClaimMark constructs reproducible, high-dimensional carriers from secret keys and shapes their frequency content and spatial amplitude while constraining their deviation from the original pseudorandom directions. Decoder-differential embedding adds only the watermark-induced change in variational autoencoder (VAE) decoder output to the original image, avoiding transfer of the VAE's reconstruction error. Given a suspect image and a trusted original, the verifier compares the observed residual with a regenerated key-specific template using spatial and spectral correlations. It accepts a claim only when the score satisfies both absolute and decoy-relative thresholds. ClaimMark requires no watermark-specific training, diffusion inversion, or iterative latent optimization. It achieves PSNR values of $51.20$ dB on MS-COCO and $53.51$ dB on DiffusionDB. Across the evaluated attribution conditions, average genuine-claim acceptance is $99.20\%$ and wrong-key acceptance is $0.162\%$. These results support reference-assisted key verification under the evaluated image transformations.