D2RA: Dual Domain Regeneration Attack

The growing use of generative models has intensified the need for watermarking methods that ensure content attribution and provenance. While recent semantic watermarking schemes improve robustness by embedding signals in latent or frequency representations, we show they remain vulnerable even under resource-constrained adversarial settings. We present D2RA, a training-free, single-image attack that removes or weakens watermarks without access to the underlying model. By projecting watermarked images onto natural priors across complementary representations, D2RA suppresses watermark signals while preserving visual fidelity. Experiments across diverse watermarking schemes demonstrate that our approach consistently reduces watermark detectability, revealing fundamental weaknesses in current designs. Our code is available at https://github.com/Pragati-Meshram/DAWN.

Key Contributions

• Training-free, single-image watermark removal attack (D2RA) requiring no access to the watermarking model or its internals
• Dual-domain projection strategy that suppresses watermark signals across complementary latent/frequency representations while preserving visual fidelity
• Systematic demonstration of fundamental weaknesses in current semantic watermarking schemes under resource-constrained adversarial settings

🛡️ Threat Analysis

Details

Similar Papers