Imagen de Portada

DP-aware AdaLN-Zero: Taming Conditioning-Induced Heavy-Tailed Gradients in Differentially Private Diffusion

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Tao, Meng, Jiayang, Yang, Xu, Hou, Chen, Chen, Hong
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Gradient-Guided Conditional Diffusion Models for Private Image Reconstruction: Analyzing Adversarial Impacts of Differential Privacy and Denoising
por: Huang, Tao, et al.
Publicado: (2024)

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

Enhanced Privacy Leakage from Noise-Perturbed Gradients via Gradient-Guided Conditional Diffusion Models
por: Meng, Jiayang, et al.
Publicado: (2025)

Mitigating Membership Inference in Intermediate Representations with Differentially Private Training
por: Meng, Jiayang, et al.
Publicado: (2026)

LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation
por: Lan, Yushi, et al.
Publicado: (2024)

Enhancing DP-SGD through Non-monotonous Adaptive Scaling Gradient Weight
por: Huang, Tao, et al.
Publicado: (2024)

Differentially Private Integrated Decision Gradients (IDG-DP) for Radar-based Human Activity Recognition
por: Zakariyya, Idris, et al.
Publicado: (2024)

InterAnimate: Taming Region-aware Diffusion Model for Realistic Human Interaction Animation
por: Lin, Yukang, et al.
Publicado: (2025)

StableDub: Taming Diffusion Prior for Generalized and Efficient Visual Dubbing
por: Chen, Liyang, et al.
Publicado: (2025)

Zero-1-to-G: Taming Pretrained 2D Diffusion Model for Direct 3D Generation
por: Meng, Xuyi, et al.
Publicado: (2025)

Real-Time Privacy Risk Measurement with Privacy Tokens for Gradient Leakage
por: Meng, Jiayang, et al.
Publicado: (2025)

DP-CSGP: Differentially Private Stochastic Gradient Push with Compressed Communication
por: Zhu, Zehan, et al.
Publicado: (2025)

Heavy-Tailed Class-Conditional Priors for Long-Tailed Generative Modeling
por: Bouayed, Aymene Mohammed, et al.
Publicado: (2025)

DiP: Taming Diffusion Models in Pixel Space
por: Chen, Zhennan, et al.
Publicado: (2025)

Intermediate Outputs Are More Sensitive Than You Think
por: Huang, Tao, et al.
Publicado: (2024)

Taming Diffusion Probabilistic Models for Character Control
por: Chen, Rui, et al.
Publicado: (2024)

ControlSR: Taming Diffusion Models for Consistent Real-World Image Super Resolution
por: Wan, Yuhao, et al.
Publicado: (2024)

DP-TLDM: Differentially Private Tabular Latent Diffusion Model
por: Zhu, Chaoyi, et al.
Publicado: (2024)

Differentially Private Fine-Tuning of Diffusion Models
por: Tsai, Yu-Lin, et al.
Publicado: (2024)

UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation
por: Sun, Yang-Tian, et al.
Publicado: (2025)

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

LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision
por: Li, Chunyu, et al.
Publicado: (2024)

Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower Resolutions
por: Khorram, Saeed, et al.
Publicado: (2024)

TransAnimate: Taming Layer Diffusion to Generate RGBA Video
por: Chen, Xuewei, et al.
Publicado: (2025)

DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks
por: Li, Yinqi, et al.
Publicado: (2025)

DP-LDMs: Differentially Private Latent Diffusion Models
por: Liu, Michael F., et al.
Publicado: (2023)

Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputs
por: Zhong, Yingji, et al.
Publicado: (2025)

SemDP: Semantic-level Differential Privacy Protection for Face Datasets
por: Zhang, Xiaoting, et al.
Publicado: (2024)

TACO: Taming Diffusion for in-the-wild Video Amodal Completion
por: Lu, Ruijie, et al.
Publicado: (2025)

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

Taming Outlier Tokens in Diffusion Transformers
por: Wu, Xiaoyu, et al.
Publicado: (2026)

E-MD3C: Taming Masked Diffusion Transformers for Efficient Zero-Shot Object Customization
por: Pham, Trung X., et al.
Publicado: (2025)

Gradient Inversion of Federated Diffusion Models
por: Huang, Jiyue, et al.
Publicado: (2024)

On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance
por: Tang, Qiaoyue, et al.
Publicado: (2025)

Taming the Heavy Tail: Age-Optimal Preemption
por: Li, Aimin, et al.
Publicado: (2026)

Denoising Diffusion Step-aware Models
por: Yang, Shuai, et al.
Publicado: (2023)

AdaQual-Diff: Diffusion-Based Image Restoration via Adaptive Quality Prompting
por: Su, Xin, et al.
Publicado: (2025)

Diffusion Reward: Learning Rewards via Conditional Video Diffusion
por: Huang, Tao, et al.
Publicado: (2023)

Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation
por: Zhang, Lilin, et al.
Publicado: (2026)

AdaOcc: Adaptive-Resolution Occupancy Prediction
por: Chen, Chao, et al.
Publicado: (2024)