LambdaMark is the first generic radioactive audio watermark that injects multi-bit messages into semantic latent representations, achieving robustness to distortions and removal attacks even after downstream model finetuning.
hub
Tree-ring watermarks: Fingerprints for diffu- sion images that are invisible and robust
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3representative 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.
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.
Presents dynamics-level watermarking for flow matching models via random coding over continuous channels, embedding key-dependent perturbations in the velocity field that preserve the generated distribution and enable black-box message recovery.
Timestep embeddings in diffusion models function as a separable side channel that can carry dedicated information for adversarial injection or detection.
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.
FSNet detects unknown invisible watermarks via adaptive frequency gating and multi-spectral attention on the UniFreq-100K dataset, claiming superior zero-shot performance.
RDSplat is the first 3D Gaussian Splatting watermarking method that maintains 0.701 bit accuracy against both 2D and 3D diffusion editing by embedding only in low-frequency primitives selected via FAPS.
A method to fingerprint VLA and WAM policies by keyed Gaussian noise seeds enables reliable ownership verification from partial outputs with minimal performance impact.
CAT trains watermark detectors against adaptive compositional adversaries using differentiable attack selection, yielding up to 63.5% capacity gains on hard attacks versus random-augmentation baselines.
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
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.
A detector that trains a separate LoRA adapter per generator and mixes them with a learned router reports the best mean accuracy on AIGIBench and Chameleon, with weaker per-dataset results on several subsets.
Major watermarking benchmarks omit cross-lingual, cultural, and demographic reporting, creating a pluralistic evaluation gap that current governance mandates ignore.
C2PA manifests and AI watermarks can independently validate contradictory claims on the same asset, and a cross-layer audit protocol resolves this with 100% accuracy on 3500 images.
SEAL uses semantic embeddings and locality-sensitive hashing to create distortion-free, database-free watermarks for generative images that are conditioned on content for improved forgery resistance.
The paper analyzes evolving security and safety threats in generative AI from content generation to agentic actions, noting that attack surfaces expand faster than defenses and that many safeguards require institutional coordination not yet in place.
citing papers explorer
-
LambdaMark: Semantic Audio Watermarking for Robustness and Radioactivity
LambdaMark is the first generic radioactive audio watermark that injects multi-bit messages into semantic latent representations, achieving robustness to distortions and removal attacks even after downstream model finetuning.
-
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.
-
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.
-
Dynamics-Level Watermarking of Flow Matching Models with Random Codes
Presents dynamics-level watermarking for flow matching models via random coding over continuous channels, embedding key-dependent perturbations in the velocity field that preserve the generated distribution and enable black-box message recovery.
-
Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding
Timestep embeddings in diffusion models function as a separable side channel that can carry dedicated information for adversarial injection or detection.
-
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.
-
AWPD: Frequency Shield Network for Agnostic Watermark Presence Detection
FSNet detects unknown invisible watermarks via adaptive frequency gating and multi-spectral attention on the UniFreq-100K dataset, claiming superior zero-shot performance.
-
RDSplat: Robust Watermarking for 3D Gaussian Splatting Against 2D and 3D Diffusion Editing
RDSplat is the first 3D Gaussian Splatting watermarking method that maintains 0.701 bit accuracy against both 2D and 3D diffusion editing by embedding only in low-frequency primitives selected via FAPS.
-
A Watermark for Vision-Language-Action and World Action Models
A method to fingerprint VLA and WAM policies by keyed Gaussian noise seeds enables reliable ownership verification from partial outputs with minimal performance impact.
-
Compositional Adversarial Training for Robust Visual Watermarking
CAT trains watermark detectors against adaptive compositional adversaries using differentiable attack selection, yielding up to 63.5% capacity gains on hard attacks versus random-augmentation baselines.
-
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
-
"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.
-
LEGO: LoRA-Enabled Generator-Oriented Framework for Synthetic Image Detection
A detector that trains a separate LoRA adapter per generator and mixes them with a learned router reports the best mean accuracy on AIGIBench and Chameleon, with weaker per-dataset results on several subsets.
-
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.
-
Authenticated Contradictions from Desynchronized Provenance and Watermarking
C2PA manifests and AI watermarks can independently validate contradictory claims on the same asset, and a cross-layer audit protocol resolves this with 100% accuracy on 3500 images.
-
SEAL: Semantic Aware Image Watermarking
SEAL uses semantic embeddings and locality-sensitive hashing to create distortion-free, database-free watermarks for generative images that are conditioned on content for improved forgery resistance.
-
From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI
The paper analyzes evolving security and safety threats in generative AI from content generation to agentic actions, noting that attack surfaces expand faster than defenses and that many safeguards require institutional coordination not yet in place.