Image de couverture de livre

SERUM: Simple, Efficient, Robust, and Unifying Marking for Diffusion-based Image Generation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kociszewski, Jan, Jastrzębski, Hubert, Stępkowski, Tymoteusz, Manijak, Filip, Rojek, Krzysztof, Boenisch, Franziska, Dziedzic, Adam
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Radioactive Watermarks in Diffusion and Autoregressive Image Generative Models
par: Meintz, Michel, et autres
Publié: (2025)

BitMark: Watermarking Bitwise Autoregressive Image Generative Models
par: Kerner, Louis, et autres
Publié: (2025)

Beautiful Images, Toxic Words: Understanding and Addressing Offensive Text in Generated Images
par: Kumar, Aditya, et autres
Publié: (2025)

Privacy Attacks on Image AutoRegressive Models
par: Kowalczuk, Antoni, et autres
Publié: (2025)

Precise Parameter Localization for Textual Generation in Diffusion Models
par: Staniszewski, Łukasz, et autres
Publié: (2025)

Implementing Adaptations for Vision AutoRegressive Model
par: Shaikh, Kaif, et autres
Publié: (2025)

Finding DoRI: Discovery of Retained Images in Diffusion Models
par: Kowalczuk, Antoni, et autres
Publié: (2025)

Localizing Memorization in SSL Vision Encoders
par: Wang, Wenhao, et autres
Publié: (2024)

Localizing and Mitigating Memorization in Image Autoregressive Models
par: Kasliwal, Aditya, et autres
Publié: (2025)

CDI: Copyrighted Data Identification in Diffusion Models
par: Dubiński, Jan, et autres
Publié: (2024)

Demystifying Foreground-Background Memorization in Diffusion Models
par: Di, Jimmy Z., et autres
Publié: (2025)

Conditioned Activation Transport for T2I Safety Steering
par: Chrabąszcz, Maciej, et autres
Publié: (2026)

ADAGE: Active Defenses Against GNN Extraction
par: Xu, Jing, et autres
Publié: (2025)

Captured by Captions: On Memorization and its Mitigation in CLIP Models
par: Wang, Wenhao, et autres
Publié: (2025)

Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks
par: Kowalczuk, Antoni, et autres
Publié: (2024)

Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models
par: Hintersdorf, Dominik, et autres
Publié: (2024)

Unlocking Post-hoc Dataset Inference with Synthetic Data
par: Zhao, Bihe, et autres
Publié: (2025)

Curation Leaks: Membership Inference Attacks against Data Curation for Machine Learning
par: Wahdany, Dariush, et autres
Publié: (2026)

Memorization in Graph Neural Networks
par: Jamadandi, Adarsh, et autres
Publié: (2025)

Differentially Private Prototypes for Imbalanced Transfer Learning
par: Wahdany, Dariush, et autres
Publié: (2024)

Adversarial Attacks and Defenses on Graph-aware Large Language Models (LLMs)
par: Olatunji, Iyiola E., et autres
Publié: (2025)

DP-GPL: Differentially Private Graph Prompt Learning
par: Xu, Jing, et autres
Publié: (2025)

Efficient Model-Stealing Attacks Against Inductive Graph Neural Networks
par: Podhajski, Marcin, et autres
Publié: (2024)

On the Privacy Risk of In-context Learning
par: Duan, Haonan, et autres
Publié: (2024)

Have it your way: Individualized Privacy Assignment for DP-SGD
par: Boenisch, Franziska, et autres
Publié: (2023)

Differentially Private Federated Learning With Time-Adaptive Privacy Spending
par: Kiani, Shahrzad, et autres
Publié: (2025)

Memorization in Self-Supervised Learning Improves Downstream Generalization
par: Wang, Wenhao, et autres
Publié: (2024)

On Stealing Graph Neural Network Models
par: Podhajski, Marcin, et autres
Publié: (2025)

Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs
par: Wang, Xun, et autres
Publié: (2025)

A Simple Approach to Unifying Diffusion-based Conditional Generation
par: Li, Xirui, et autres
Publié: (2024)

SuperMark: Robust and Training-free Image Watermarking via Diffusion-based Super-Resolution
par: Hu, Runyi, et autres
Publié: (2024)

Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives
par: Hanke, Vincent, et autres
Publié: (2024)

DiffMark: Diffusion-based Robust Watermark Against Deepfakes
par: Sun, Chen, et autres
Publié: (2025)

UniMark: Unified Adaptive Multi-bit Watermarking for Autoregressive Image Generators
par: Yilmaz, Yigit, et autres
Publié: (2026)

MUC: Machine Unlearning for Contrastive Learning with Black-box Evaluation
par: Wang, Yihan, et autres
Publié: (2024)

ClusterMark: Towards Robust Watermarking for Autoregressive Image Generators with Visual Token Clustering
par: Lukovnikov, Denis, et autres
Publié: (2025)

Efficient Image-to-Image Diffusion Classifier for Adversarial Robustness
par: Mei, Hefei, et autres
Publié: (2024)

Context Diffusion: In-Context Aware Image Generation
par: Najdenkoska, Ivona, et autres
Publié: (2023)

LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation
par: Wang, Jiahao, et autres
Publié: (2025)

Visual Affect Analysis: Predicting Emotions of Image Viewers with Vision-Language Models
par: Nowicki, Filip, et autres
Publié: (2026)