GIFGuard is the first spatiotemporal watermarking framework for proactive deepfake forensics in facial GIFs, using a 3D adaptive residual encoder and hourglass decoder plus a new GIFfaces dataset.
Robust invisible video watermarking with attention
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 2polarities
background 2representative citing papers
Re-watermarking reliably removes existing watermarks across 96 dataset-victim-attack combinations and pairs with a classifier achieving 0.878-0.953 accuracy, cutting bit accuracy by 25-48%.
CAT trains watermark detectors against adaptive compositional adversaries using differentiable attack selection, yielding up to 63.5% capacity gains on hard attacks versus random-augmentation baselines.
PGID restores watermark detection in diffusion models by using progressive inversion-denoising cycles to correct latents displaced by removal or forgery attacks.
ISTS watermarking dynamically controls injection based on prompt semantics and uses two-sided detection to resist removal and forgery attacks in diffusion models.
Randomized per-query key selection with single-key detection acceptance bounds forgery success rate independently of collected samples while preserving model utility.
citing papers explorer
-
GIFGuard: Proactive Forensics against Deepfakes in Facial GIFs via Spatiotemporal Watermarking
GIFGuard is the first spatiotemporal watermarking framework for proactive deepfake forensics in facial GIFs, using a 3D adaptive residual encoder and hourglass decoder plus a new GIFfaces dataset.
-
Watermarks Attack Watermarks: Re-Watermarking as a Generic Removal Strategy
Re-watermarking reliably removes existing watermarks across 96 dataset-victim-attack combinations and pairs with a classifier achieving 0.878-0.953 accuracy, cutting bit accuracy by 25-48%.
-
Compositional Adversarial Training for Robust Visual Watermarking
CAT trains watermark detectors against adaptive compositional adversaries using differentiable attack selection, yielding up to 63.5% capacity gains on hard attacks versus random-augmentation baselines.
-
PGID: Progressive Guided Inversion and Denoising for Robust Watermark Detection
PGID restores watermark detection in diffusion models by using progressive inversion-denoising cycles to correct latents displaced by removal or forgery attacks.
-
Towards Robust Content Watermarking Against Removal and Forgery Attacks
ISTS watermarking dynamically controls injection based on prompt semantics and uses two-sided detection to resist removal and forgery attacks in diffusion models.
-
Mitigating Watermark Forgery in Generative Models via Randomized Key Selection
Randomized per-query key selection with single-key detection acceptance bounds forgery success rate independently of collected samples while preserving model utility.