arXiv Computer Vision
Membership is Ownership: A Robust Ownership Verification Framework for Diffusion Models
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Aug 13
Fingerprinting Text-to-Image Diffusion Models via Collapsed Generation
arXiv:2608. 11732v1 Announce Type: cross Abstract: Proprietary text-to-image diffusion models are increasingly distributed as hosted services and downloadable checkpoints, making their intellectual property (IP) protection an increasingly critical concern when model leakage, copying, or unauthorized fine-tuning is disputed.
arXiv Machine Learning
Jun 30
Proofs of Ownership for Machine Learning Models
arXiv:2606. 30423v1 Announce Type: new Abstract: With the increasing adoption of Machine Learning, protecting model ownership has become an essential challenge.
arXiv AI
Aug 7
Revisiting Black-Box Model Ownership Verification through Information Theory
arXiv:2409. 06130v2 Announce Type: replace-cross Abstract: Modern machine learning models require substantial computational resources and data to train, making them valuable intellectual property.
arXiv Machine Learning
2d ago
CertDW: Towards Certified Dataset Ownership Verification via Conformal Calibration
The paper introduces CertDW, a certified dataset watermark and ownership verification method that remains reliable even under malicious perturbations. By leveraging conformal prediction, it defines two statistical measures—principal probability (PP) and watermark robustness (WR)—to evaluate model stability on benign versus watermarked samples. The authors derive certification conditions linking WR to a PP-based threshold and provide a high‑probability bound on false positives, enabling robust ownership verification when a suspicious model’s WR exceeds the PP values of benign models.
arXiv Machine Learning
Jul 27
DCS: A Unified Conditional Sensitivity Framework for Cross-Modal Copyright Infringement Detection
arXiv:2607. 22035v1 Announce Type: new Abstract: Currently, most foundation models can reproduce or strongly depend on copyrighted training content, but output similarity alone is insufficient for infringement detection, because similar outputs may also arise from public-domain concepts, common stylistic conventions, or ordinary statistical generalization.
arXiv AI
Jun 11
T2S: A Rehearsal-Based Approach for Extraction-Resistant Model Watermarking
arXiv:2606. 11698v1 Announce Type: cross Abstract: Model watermarking safeguards AI model intellectual property by embedding distinctive knowledge that induces unique behavioral signatures.