Pith. sign in

REVIEW 4 cited by

TrustMark: Universal Watermarking for Arbitrary Resolution Images

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.18297 v1 pith:FVFG376Q submitted 2023-11-30 cs.CV cs.AI

Tu Bui , Shruti Agarwal , John Collomosse This is my paper · ORCID
classification cs.CVcs.AI
keywords watermarkingarbitraryimageimagesmethodresolutiontrustmarkwatermark
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Imperceptible digital watermarking is important in copyright protection, misinformation prevention, and responsible generative AI. We propose TrustMark - a GAN-based watermarking method with novel design in architecture and spatio-spectra losses to balance the trade-off between watermarked image quality with the watermark recovery accuracy. Our model is trained with robustness in mind, withstanding various in- and out-place perturbations on the encoded image. Additionally, we introduce TrustMark-RM - a watermark remover method useful for re-watermarking. Our methods achieve state-of-art performance on 3 benchmarks comprising arbitrary resolution images.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ResGuard: Enhancing Robustness Against Known Original Attacks in Deep Watermarking

    cs.CV 2026-04 accept novelty 6.5 of 10

    ResGuard makes deep-watermark residuals image-specific via a contrastive loss and KOA noise layer, restoring near-perfect extraction under residual-subtraction attacks that previously collapsed accuracy to chance.

  2. LoT-Pass: Long-term-robust Image Watermarking for Image to Video Generation

    cs.CV 2025-09 conditional novelty 6.0 of 10

    I2VWM uses video-like training distortions and optical-flow frame alignment to keep image watermarks decodable in AI-generated videos made from that image.

  3. IConMark: Robust Interpretable Concept-Based Watermark For AI Images

    cs.CV 2025-07 conditional novelty 6.0 of 10

    IConMark adds preselected, human-readable objects to AI images via prompt engineering and detects them with a vision-language model, achieving higher AUROC than noise-based watermarks on tested augmentations.

  4. SPFM-Net: Semantic-Prior-Guided Frequency-Constrained Mamba for Invisible Watermark Attack

    cs.CV 2026-07 reject novelty 5.0 of 10

    SPFM-Net attacks invisible watermarks by reconstructing heavily masked images with a pretrained semantic model; it reports good removal on Stable Signature/HiDDeN but poor removal on Yu.

Pith tools