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.
A recipe for watermarking diffusion models
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
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.
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 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 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 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 embeds authorization into diffusion models via a learnable signature network that assigns input-specific signatures, blocking unauthorized use while preserving quality for authorized queries.
Introduces an efficient fingerprinting method for diffusion models with built-in protection against collusion attacks through parameter transformations that degrade colluded model performance.
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 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.
ISTS watermarking dynamically controls injection based on prompt semantics and uses two-sided detection to resist removal and forgery attacks in diffusion models.
citing papers explorer
-
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.
-
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.