Removing Watermarks with Partial Regeneration using Semantic Information
By: Krti Tallam , John Kevin Cava , Caleb Geniesse and more
Potential Business Impact:
Removes hidden marks from AI pictures.
As AI-generated imagery becomes ubiquitous, invisible watermarks have emerged as a primary line of defense for copyright and provenance. The newest watermarking schemes embed semantic signals - content-aware patterns that are designed to survive common image manipulations - yet their true robustness against adaptive adversaries remains under-explored. We expose a previously unreported vulnerability and introduce SemanticRegen, a three-stage, label-free attack that erases state-of-the-art semantic and invisible watermarks while leaving an image's apparent meaning intact. Our pipeline (i) uses a vision-language model to obtain fine-grained captions, (ii) extracts foreground masks with zero-shot segmentation, and (iii) inpaints only the background via an LLM-guided diffusion model, thereby preserving salient objects and style cues. Evaluated on 1,000 prompts across four watermarking systems - TreeRing, StegaStamp, StableSig, and DWT/DCT - SemanticRegen is the only method to defeat the semantic TreeRing watermark (p = 0.10 > 0.05) and reduces bit-accuracy below 0.75 for the remaining schemes, all while maintaining high perceptual quality (masked SSIM = 0.94 +/- 0.01). We further introduce masked SSIM (mSSIM) to quantify fidelity within foreground regions, showing that our attack achieves up to 12 percent higher mSSIM than prior diffusion-based attackers. These results highlight an urgent gap between current watermark defenses and the capabilities of adaptive, semantics-aware adversaries, underscoring the need for watermarking algorithms that are resilient to content-preserving regenerative attacks.
Similar Papers
SEAL: Semantic Aware Image Watermarking
Machine Learning (CS)
Marks AI pictures so you know they're fake.
Diffusion-Based Image Editing for Breaking Robust Watermarks
CV and Pattern Recognition
Breaks hidden messages in pictures using AI.
PT-Mark: Invisible Watermarking for Text-to-image Diffusion Models via Semantic-aware Pivotal Tuning
Cryptography and Security
Keeps AI art looking the same, but tracks its owner.