Search papers, labs, and topics across Lattice.
This paper introduces SpreadMark, a novel approach to image watermarking that utilizes spread-spectrum embedding to enhance robustness against both incidental distortions and deliberate removal attempts. By spreading each watermark bit as a dense pseudo-random codeword across the entire image, the method significantly increases the difficulty of disrupting watermark recovery compared to traditional encoder-decoder schemes. Evaluations on COCO and DIV2K datasets show that SpreadMark outperforms existing methods in maintaining high detection rates while preserving perceptual quality, even under challenging conditions like regeneration and latent-space sparsification.
SpreadMark's innovative dense pseudo-random codeword embedding makes watermarking significantly more resilient to attacks, outperforming traditional methods in both robustness and imperceptibility.
Invisible image watermarks are increasingly used for deepfake detection and provenance tracking, where they must survive not only incidental distortions but also deliberate removal. We revisit spread-spectrum embedding, a classical watermarking principle, inside a modern neural post-hoc watermarking architecture. Our starting point is a measurement: in existing encoder-decoder schemes each message bit occupies only a small fraction of the image, a shared contributing factor to their fragility, since removal then need only disturb the region a bit occupies. SpreadMark instead spreads each bit as a dense pseudo-random codeword over the whole image and recovers it by matched-filtering a learned cover-suppressed chip representation, with a parallel convolutional decoding path and sparsification-aware training. A conditional chip-space analysis shows that, under a codeword-independent perturbation model, dense spreading increases the budget required to disrupt matched-filter recovery. Evaluated on COCO and DIV2K against nine schemes, SpreadMark is the only evaluated method retaining high detection under both the regeneration and the latent-space sparsification settings we test, with competitive JPEG and additive-noise robustness. It keeps the embedded watermark imperceptible, maintaining high perceptual quality on both COCO and DIV2K.
