Adaptive Optimization for Stable High-Capacity CNN/GAN Image Watermarking

Deep learning-based image watermarking must balance perceptual transparency and reliable watermark recovery, and this balance becomes harder to optimize as the payload grows. This paper presents an adaptive optimization framework for stable high-capacity CNN/GAN image watermarking, in which the composition of the loss function, the weighting of its components and the regularization strength are adapted to the watermark complexity. The framework is evaluated with a fixed architecture for payloads from 16 to 16,384 bits in a distortion-free channel, using baseline, simplified no-mapper and attention-extended configurations, with paired significance tests and Holm–Bonferroni correction on an independent test set. The mapper reconstruction term is shown to provide no gradient, so its removal leaves the gradient unchanged and reduces the per-epoch training time by up to about 40% at high capacity. The run-to-run variability of adversarial training, estimated from gradient-equivalent runs, reaches a median of 0.66 dB in PSNR and is comparable to the effect of the loss weights, while the selected weights and weight decay depend on the watermark complexity. In a pilot study, an attention module improved transparency and decoding reliability mainly at higher capacities. The study provides practical guidance for the design and evaluation of optimization procedures in high-capacity watermarking.

Authors

Institutions

Publication Details

Journal
Applied Sciences
Published
2026-11-19
DOI
https://doi.org/10.3390/app162211464
Citations
1
Primary Topic
Advanced Steganography and Watermarking Techniques
Type
article
Field-Weighted Citation Impact
1.10
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Adaptive Optimization for Stable High-Capacity CNN/GAN Image Watermarking

Marta Bistroń, Zbigniew Piotrowski
1 citations
Applied Sciences
Advanced Steganography and Watermarking Techniques
1.10
article

Adaptive Optimization for Stable High-Capacity CNN/GAN Image Watermarking

Marta Bistroń, Zbigniew Piotrowski
article en
1 citations

Abstract

Deep learning-based image watermarking must balance perceptual transparency and reliable watermark recovery, and this balance becomes harder to optimize as the payload grows. This paper presents an adaptive optimization framework for stable high-capacity CNN/GAN image watermarking, in which the composition of the loss function, the weighting of its components and the regularization strength are adapted to the watermark complexity. The framework is evaluated with a fixed architecture for payloads from 16 to 16,384 bits in a distortion-free channel, using baseline, simplified no-mapper and attention-extended configurations, with paired significance tests and Holm–Bonferroni correction on an independent test set. The mapper reconstruction term is shown to provide no gradient, so its removal leaves the gradient unchanged and reduces the per-epoch training time by up to about 40% at high capacity. The run-to-run variability of adversarial training, estimated from gradient-equivalent runs, reaches a median of 0.66 dB in PSNR and is comparable to the effect of the loss weights, while the selected weights and weight decay depend on the watermark complexity. In a pilot study, an attention module improved transparency and decoding reliability mainly at higher capacities. The study provides practical guidance for the design and evaluation of optimization procedures in high-capacity watermarking.

Applied SciencesVol. 16(22)
Military University of Technology in Warsaw (PL)
Openalex Percentile: Top 26%
Advanced Steganography and Watermarking Techniques
1.10
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon