Papers for

software developers building content verification tools

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Nawe combines neural networks with signal processing for better digital watermarking

NAWE: Digital Watermarking with Neural-Assisted Watermark Extraction

Abstract: NAWE (Neural-Assisted Watermark Extraction) combines an explicit signal-processing watermarking construction with a pretrained neural host predictor. A periodic, perceptually masked watermark carrier provides synchronization, Polar coding supplies redundancy, and denoising followed by subtraction extracts the embedded watermark. The denoiser remains frozen, without watermark-specific training. A one-factor-at-a-time study compares Wiener, BM3D, DRUNet, and GS-DRUNet host estimators. Comparisons with TrustMark, SSL Watermarking, PixelSeal, and WAM show NAWE's lowest geometric and photometric class BER and strong message recovery, while filtering and noise remain limitations consistent with the non-adaptive selection of the watermark extractor. The comparison retains the systems' different payloads and coding.

Tue 22 SeptComputer Vision and Pattern RecognitionMultimedia
The gist
Digital watermarking hides secret information in images to prove ownership or authenticity. The authors propose NAWE, a method that mixes traditional signal processing with a neural network trained to predict the original image, helping to better extract the hidden watermark. Their approach uses a special pattern and error-correcting codes to reliably recover the message, even after the image is altered. They tested several neural network models and found their method recovers watermarks more accurately than some existing systems, though noise and filtering still create challenges.
Open → 2609.25972v1