REVIEW 14 cited by
A Recipe for Watermarking Diffusion Models
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
A Recipe for Watermarking Diffusion Models
read the original abstract
Diffusion models (DMs) have demonstrated advantageous potential on generative tasks. Widespread interest exists in incorporating DMs into downstream applications, such as producing or editing photorealistic images. However, practical deployment and unprecedented power of DMs raise legal issues, including copyright protection and monitoring of generated content. In this regard, watermarking has been a proven solution for copyright protection and content monitoring, but it is underexplored in the DMs literature. Specifically, DMs generate samples from longer tracks and may have newly designed multimodal structures, necessitating the modification of conventional watermarking pipelines. To this end, we conduct comprehensive analyses and derive a recipe for efficiently watermarking state-of-the-art DMs (e.g., Stable Diffusion), via training from scratch or finetuning. Our recipe is straightforward but involves empirically ablated implementation details, providing a foundation for future research on watermarking DMs. The code is available at https://github.com/yunqing-me/WatermarkDM.
Forward citations
Cited by 14 Pith papers
-
Proofs of Ownership for Machine Learning Models
A formal game-based study establishes that black-box proofs of ownership for ML classifiers are possible precisely when the concept class is not self-correctable.
-
The Coding Limits of Robust Watermarking for Generative Models
Establishes an unconditional robustness threshold of 1-1/q for zero-bit tamper-detection codes in watermarking, with matching constructions and experimental confirmation on image models.
-
RaMark: Radioactive Watermarking for Generated Tabular Data
A sinusoidal dependency embedded as part of the tabular distribution remains detectable after generative retraining and data-modification attacks while utility is preserved.
-
Diffusion Model Attribution via Spectral Coupling of Denoiser Responses
SDS extracts stable spectral signatures from diffusion model denoisers via frequency-controlled perturbations, achieving 99.9% attribution accuracy across eight models and 96.2% under prompt shift.
-
LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models
LoRA-Key creates a standalone user-specific Watermark LoRA trained with a latent watermark prior and GOP, attachable via training-free superposition to protect LoRA ownership while preserving quality.
-
COPYCOP: Ownership Verification for Graph Neural Networks
COPYCOP identifies copycat GNNs by matching their node embeddings despite architectural differences and adversarial transformations, backed by theoretical guarantees and tests on 14 datasets across 5 architectures.
-
CSF: Black-box Fingerprinting via Compositional Semantics for Text-to-Image Models
CSF is the first black-box method to attribute fine-tuned text-to-image models to original lineages via compositional semantic probes and Bayesian decisions across multiple model families.
-
GoodDiffusion: Proactive Copyright Protection for Diffusion Bridge Models via Learnable Sample-specific Signatures
GoodDiffusion embeds authorization into diffusion models via a learnable signature network that assigns input-specific signatures, blocking unauthorized use while preserving quality for authorized queries.
-
Efficient, Robust, and Anti-Collusion Fingerprinting of Image Diffusion Models
Introduces an efficient fingerprinting method for diffusion models with built-in protection against collusion attacks through parameter transformations that degrade colluded model performance.
-
"Training robust watermarking model may hurt authentication!'' Exploring and Mitigating the Identity Leakage in Robust Watermarking
W-IR is the first watermarking framework to combine certified robustness via randomized smoothing in pixel and coordinate spaces with identity leakage mitigation via residual information loss minimization.
-
Dual-Guard: Dual-Channel Latent Watermarking for Provenance and Tamper Localization in Diffusion Images
Dual-Guard embeds complementary watermarks in diffusion image generation to verify provenance and localize tampering with low error rates on a 2400-sample benchmark under reprompting and editing 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.
-
Position: AI/ML Deepfake Research is Misaligned with AI-Generated Non-Consensual Intimate Imagery (AIG-NCII)
The dominant real-world use of generative-image abuse is non-consensual intimate imagery, yet the AI/ML research field focuses almost exclusively on viewer deception.
-
Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach
Existing dataset watermarks for diffusion fine-tuning transfer well across models and tasks but remain vulnerable to a proposed restoration-based removal attack (DeAttack), whose claimed full removal is not fully demo...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.