REVIEW 8 cited by
WAVES: Benchmarking the Robustness of Image Watermarks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
In the burgeoning age of generative AI, watermarks act as identifiers of provenance and artificial content. We present WAVES (Watermark Analysis Via Enhanced Stress-testing), a benchmark for assessing image watermark robustness, overcoming the limitations of current evaluation methods. WAVES integrates detection and identification tasks and establishes a standardized evaluation protocol comprised of a diverse range of stress tests. The attacks in WAVES range from traditional image distortions to advanced, novel variations of diffusive, and adversarial attacks. Our evaluation examines two pivotal dimensions: the degree of image quality degradation and the efficacy of watermark detection after attacks. Our novel, comprehensive evaluation reveals previously undetected vulnerabilities of several modern watermarking algorithms. We envision WAVES as a toolkit for the future development of robust watermarks. The project is available at https://wavesbench.github.io/
Forward citations
Cited by 8 Pith papers
-
Beyond Invisibility: Learning Robust Visible Watermarks for Stronger Copyright Protection
HARVIM learns watermark placement to maximize reconstruction error under an inpainting-based removal model, showing modest gains over random watermarks.
-
Robust Watermarks Leak: Channel-Aware Feature Extraction Enables Adversarial Watermark Manipulation
Robust watermarks leak detectable patterns into neural network feature channels, enabling single-image, no-box watermark removal and forgery.
-
Who Gets Flagged? The Pluralistic Evaluation Gap in AI Content Watermarking
Major watermarking benchmarks omit cross-lingual, cultural, and demographic reporting, creating a pluralistic evaluation gap that current governance mandates ignore.
-
IConMark: Robust Interpretable Concept-Based Watermark For AI Images
IConMark adds preselected, human-readable objects to AI images via prompt engineering and detects them with a vision-language model, achieving higher AUROC than noise-based watermarks on tested augmentations.
-
Gaussian Shading++: Rethinking the Realistic Deployment Challenge of Performance-Lossless Image Watermark for Diffusion Models
Gaussian Shading++ hides an invisible watermark in diffusion images using a fixed key, storing the random seed in a pseudorandom error-correcting header and improving extraction with soft-decision decoding.
-
Watermarking Visual Concepts for Diffusion Models
ConceptWM binds a watermark to a specific visual concept in diffusion model outputs and adds adversarial noise that degrades models fine-tuned on those watermarked images.
-
When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box Setting
Blur-plus-deblur and generator fine-tuning can push watermark bit accuracy toward chance, but only when the attacker can train a surrogate decoder that matches the target's architecture.
-
Invisible Watermarks: Attacks and Robustness
Stacking StegaStamp and Tree-Ring watermarks with a remover network gives marginal robustness gains, and GradCAM-guided localized blurring reduces distortion relative to uniform blurring but not enough to beat regener...
Discussion (0). Continue with ORCID to comment.