Imagen de Portada

Differentially Private Fine-Tuning of Diffusion Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Tsai, Yu-Lin, Li, Yizhe, Chen, Zekai, Chen, Po-Yu, Yu, Chia-Mu, Ren, Xuebin, Buet-Golfouse, Francois
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Defending Unauthorized Model Merging via Dual-Stage Weight Protection
por: Chen, Wei-Jia, et al.
Publicado: (2025)

IU: Imperceptible Universal Backdoor Attack
por: Lin, Hsin, et al.
Publicado: (2026)

DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning
por: Lebensold, Jonathan, et al.
Publicado: (2024)

Differentially Private Bias-Term Fine-tuning of Foundation Models
por: Bu, Zhiqi, et al.
Publicado: (2022)

Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable
por: Liu, Haozhe, et al.
Publicado: (2024)

From Easy to Hard++: Promoting Differentially Private Image Synthesis Through Spatial-Frequency Curriculum
por: Gong, Chen, et al.
Publicado: (2026)

Fine-grained Manipulation Attacks to Local Differential Privacy Protocols for Data Streams
por: Li, Xinyu, et al.
Publicado: (2025)

RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models
por: Jiang, Tanqiu, et al.
Publicado: (2025)

Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models
por: Zhang, Lei, et al.
Publicado: (2025)

Decomposing Private Image Generation via Coarse-to-Fine Wavelet Modeling
por: Bayrooti, Jasmine, et al.
Publicado: (2026)

PrivImage: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretraining
por: Li, Kecen, et al.
Publicado: (2023)

Learning Differentially Private Diffusion Models via Stochastic Adversarial Distillation
por: Liu, Bochao, et al.
Publicado: (2024)

FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models
por: Cui, Yingqian, et al.
Publicado: (2023)

Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs
por: Wang, Hui-Po, et al.
Publicado: (2020)

Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models
por: Yang, Zijin, et al.
Publicado: (2024)

TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection
por: Jiang-Lin, Jian-Yu, et al.
Publicado: (2025)

Rethinking Robust Adversarial Concept Erasure in Diffusion Models
por: Yin, Qinghong, et al.
Publicado: (2025)

InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning
por: Sun, Mengyuan, et al.
Publicado: (2025)

Video Signature: Implicit Watermarking for Video Diffusion Models
por: Huang, Yu, et al.
Publicado: (2025)

Risks When Sharing LoRA Fine-Tuned Diffusion Model Weights
por: Yao, Dixi
Publicado: (2024)

VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models
por: Chou, Sheng-Yen, et al.
Publicado: (2023)

Gaussian Shading++: Rethinking the Realistic Deployment Challenge of Performance-Lossless Image Watermark for Diffusion Models
por: Yang, Zijin, et al.
Publicado: (2025)

Differentially Private Synthetic Data via Foundation Model APIs 1: Images
por: Lin, Zinan, et al.
Publicado: (2023)

BadBlocks: Low-Cost and Stealthy Backdoor Attacks Tailored for Text-to-Image Diffusion Models
por: Wu, Jia, et al.
Publicado: (2025)

Extracting Training Data from Unconditional Diffusion Models
por: Chen, Yunhao, et al.
Publicado: (2024)

Backdoor Mitigation in Object Detection via Adversarial Fine-Tuning
por: Dunnett, Kealan, et al.
Publicado: (2026)

Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Model
por: Lin, Zinan, et al.
Publicado: (2025)

Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion
por: Shpilevskiy, Frederick, et al.
Publicado: (2025)

REAEDP: Entropy-Calibrated Differentially Private Data Release with Formal Guarantees and Attack-Based Evaluation
por: Ma, Bo, et al.
Publicado: (2026)

Is Diffusion Model Safe? Severe Data Leakage via Gradient-Guided Diffusion Model
por: Meng, Jiayang, et al.
Publicado: (2024)

An Inversion-based Measure of Memorization for Diffusion Models
por: Ma, Zhe, et al.
Publicado: (2024)

Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models
por: Ren, Jie, et al.
Publicado: (2024)

VidLeaks: Membership Inference Attacks Against Text-to-Video Models
por: Wang, Li, et al.
Publicado: (2026)

Private Gradient Estimation is Useful for Generative Modeling
por: Liu, Bochao, et al.
Publicado: (2023)

LoyalDiffusion: A Diffusion Model Guarding Against Data Replication
por: Li, Chenghao, et al.
Publicado: (2024)

MIBench: A Comprehensive Framework for Benchmarking Model Inversion Attack and Defense
por: Qiu, Yixiang, et al.
Publicado: (2024)

Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models
por: Sato, Takami, et al.
Publicado: (2023)

EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Models
por: Chen, Ruoxi, et al.
Publicado: (2023)

Bi-Erasing: A Bidirectional Framework for Concept Removal in Diffusion Models
por: Chen, Hao, et al.
Publicado: (2025)

Guarding the Gate: ConceptGuard Battles Concept-Level Backdoors in Concept Bottleneck Models
por: Lai, Songning, et al.
Publicado: (2024)