arXiv:2610.03166v1 Announce Type: cross Abstract: Digital watermarking supports source attribution for AI-generated images, but its reliability depends on resistance to removal attacks. Some attacks...
arXiv:2608. 10166v1 Announce Type: cross Abstract: Digital watermarking has emerged as a critical technique for provenance and copyright attribution in AI-generated imagery, yet its robustness against realistic, model-agnostic removal attacks remains poorly explored.
arXiv:2610.12952v1 Announce Type: cross Abstract: Image watermarking enables provenance tracing for photorealistic images generated by diffusion models. However, state-of-the-art (SOTA) removal attac...
The paper proposes a defense against watermark forgery in generative models by randomizing the selection of watermark keys for each query and accepting content only if exactly one key detects a watermark. This approach provides a sample‑count‑independent upper bound on forgery success for blind attackers while preserving model utility. Experiments show a dramatic drop in forgery success rates—from 87% to 1% with four keys for text and from 100% to 2% for images—without significant computational overhead.
IRIS is a training‑free watermarking scheme for diffusion‑generated images that binds a watermark to the image’s visual semantics. It derives an intrinsic ring identifier from a content code of the non‑watermarked image and injects it late in the generation trajectory, ensuring the mark survives common processing while breaking under semantic changes or foreign images. Experiments on three prompt datasets show IRIS reliably detects watermarks, maintains fidelity to the original image, and resists forgery techniques that defeat other marks.
arXiv:2608.29212v1 Announce Type: cross Abstract: Existing video watermarking systems are symmetric: the party that can verify a mark holds the extractor weights or generator secret and can therefore...
WeaveMark is a new multi‑bit watermarking scheme for large language models that improves payload capacity, extraction accuracy, and text quality by using coded payload spreading, soft‑decision error‑correcting codes, and unbiased multilayer reweighting. It also adds zero‑bit layers for reliable detection of watermark presence. Experiments demonstrate significant gains, achieving an 89.8% match rate for 32‑bit messages at 200 tokens and maintaining 86.0% accuracy under 10% substitution attacks on 16‑bit messages, far outperforming the BiMark baseline.
arXiv:2610.08178v1 Announce Type: new Abstract: Existing latent-based watermarking methods for diffusion models have overestimated their robustness to image distortions, including geometric transform...
The paper introduces mAVE, a training‑free watermarking framework for joint audio‑visual diffusion transformers that binds audio and video modalities through a session‑keyed cryptographic digest. mAVE separates public record retrieval from secret session authentication, enabling provider‑assisted verification without altering generator weights or training auxiliary networks. Experiments on LTX‑2 and MOVA demonstrate high true‑positive rates (99.8%) and negligible false positives, while maintaining comparable generation quality.
arXiv:2607. 06009v1 Announce Type: cross Abstract: Attributing code to the large language model that produced it is essential for provenance, licensing, and misuse accountability, yet no deployed watermark meets this need.
Deep learning-based watermarking has shown strong robustness against non-geometric distortions, yet its performance under geometric transformations remains limited. Such transformations induce two fundamental failure modes: region removal, such as cropping or masking, which eliminates the information carried by removed pixels, and desynchronization, such as scaling or rotation, which misaligns pixel positions and disrupts decoding.
arXiv:2609.40031v1 Announce Type: cross Abstract: Digital image watermarking is increasingly critical in media contexts, as emerging regulations and industry practices require marking AI-generated co...