Image de couverture de livre

Is Diffusion Model Safe? Severe Data Leakage via Gradient-Guided Diffusion Model

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Meng, Jiayang, Huang, Tao, Chen, Hong, Li, Cuiping
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Enhanced Privacy Leakage from Noise-Perturbed Gradients via Gradient-Guided Conditional Diffusion Models
par: Meng, Jiayang, et autres
Publié: (2025)

Gradient Inversion of Federated Diffusion Models
par: Huang, Jiyue, et autres
Publié: (2024)

LoyalDiffusion: A Diffusion Model Guarding Against Data Replication
par: Li, Chenghao, et autres
Publié: (2024)

GaussMarker: Robust Dual-Domain Watermark for Diffusion Models
par: Li, Kecen, et autres
Publié: (2025)

Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Models
par: Wei, Kang, et autres
Publié: (2025)

Intermediate Outputs Are More Sensitive Than You Think
par: Huang, Tao, et autres
Publié: (2024)

Video Signature: Implicit Watermarking for Video Diffusion Models
par: Huang, Yu, et autres
Publié: (2025)

SAP-DIFF: Semantic Adversarial Patch Generation for Black-Box Face Recognition Models via Diffusion Models
par: Wang, Mingsi, et autres
Publié: (2025)

SteerDiff: Steering towards Safe Text-to-Image Diffusion Models
par: Zhang, Hongxiang, et autres
Publié: (2024)

Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
par: Zhai, Shengfang, et autres
Publié: (2024)

Controllable Adversarial Makeup for Privacy via Text-Guided Diffusion
par: Kwon, Youngjin, et autres
Publié: (2025)

An Inversion-based Measure of Memorization for Diffusion Models
par: Ma, Zhe, et autres
Publié: (2024)

MMA-Diffusion: MultiModal Attack on Diffusion Models
par: Yang, Yijun, et autres
Publié: (2023)

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings
par: Fan, Mingyuan, et autres
Publié: (2025)

Bi-Erasing: A Bidirectional Framework for Concept Removal in Diffusion Models
par: Chen, Hao, et autres
Publié: (2025)

Rethinking Robust Adversarial Concept Erasure in Diffusion Models
par: Yin, Qinghong, et autres
Publié: (2025)

Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
par: Zhang, Yimeng, et autres
Publié: (2024)

SafeText: Safe Text-to-image Models via Aligning the Text Encoder
par: Hu, Yuepeng, et autres
Publié: (2025)

Guidance Watermarking for Diffusion Models
par: Gesny, Enoal, et autres
Publié: (2025)

Gaussian Shannon: High-Precision Diffusion Model Watermarking Based on Communication
par: Zhang, Yi, et autres
Publié: (2026)

Mitigate Replication and Copying in Diffusion Models with Generalized Caption and Dual Fusion Enhancement
par: Li, Chenghao, et autres
Publié: (2023)

Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models
par: Sato, Takami, et autres
Publié: (2023)

Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling
par: Li, Zida, et autres
Publié: (2026)

Adversarial Examples are Misaligned in Diffusion Model Manifolds
par: Lorenz, Peter, et autres
Publié: (2024)

Improving Image Data Leakage Detection in Automotive Software
par: Babu, Md Abu Ahammed, et autres
Publié: (2024)

EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Models
par: Chen, Ruoxi, et autres
Publié: (2023)

Extracting Training Data from Unconditional Diffusion Models
par: Chen, Yunhao, et autres
Publié: (2024)

HMARK: Radioactive Multi-Bit Semantic-Latent Watermarking for Diffusion Models
par: Li, Kexin, et autres
Publié: (2025)

Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models
par: Yang, Zijin, et autres
Publié: (2024)

Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable
par: Liu, Haozhe, et autres
Publié: (2024)

SIDE: Surrogate Conditional Data Extraction from Diffusion Models
par: Chen, Yunhao, et autres
Publié: (2024)

Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models
par: Ren, Jie, et autres
Publié: (2024)

DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models
par: Wang, Zhenting, et autres
Publié: (2023)

SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism
par: Chen, Beitao, et autres
Publié: (2025)

Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention
par: Ren, Jie, et autres
Publié: (2024)

Robust Classification via a Single Diffusion Model
par: Chen, Huanran, et autres
Publié: (2023)

Embedding Watermarks in Diffusion Process for Model Intellectual Property Protection
par: Yang, Jijia, et autres
Publié: (2024)

LightPure: Realtime Adversarial Image Purification for Mobile Devices Using Diffusion Models
par: Khalili, Hossein, et autres
Publié: (2024)

Stable Signature is Unstable: Removing Image Watermark from Diffusion Models
par: Hu, Yuepeng, et autres
Publié: (2024)

Neighbor-Aware Localized Concept Erasure in Text-to-Image Diffusion Models
par: Shi, Zhuan, et autres
Publié: (2026)