PrivFedTalk: Privacy-Aware Federated Diffusion with Identity-Stable Adapters for Personalized Talking-Head Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Mazumdar, Soumya, Rakesh, Vineet Kumar, Samanta, Tapas
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910115925327872
author Mazumdar, Soumya
Rakesh, Vineet Kumar
Samanta, Tapas
author_facet Mazumdar, Soumya
Rakesh, Vineet Kumar
Samanta, Tapas
contents Talking-head generation has advanced rapidly with diffusion-based generative models, but training usually depends on centralized face-video and speech datasets, raising major privacy concerns. The problem is more acute for personalized talking-head generation, where identity-specific data are highly sensitive and often cannot be pooled across users or devices. PrivFedTalk is presented as a privacy-aware federated framework for personalized talking-head generation that combines conditional latent diffusion with parameter-efficient identity adaptation. A shared diffusion backbone is trained across clients, while each client learns lightweight LoRA identity adapters from local private audio-visual data, avoiding raw data sharing and reducing communication cost. To address heterogeneous client distributions, Identity-Stable Federated Aggregation (ISFA) weights client updates using privacy-safe scalar reliability signals computed from on-device identity consistency and temporal stability estimates. Temporal-Denoising Consistency (TDC) regularization is introduced to reduce inter-frame drift, flicker, and identity drift during federated denoising. To limit update-side privacy risk, secure aggregation and client-level differential privacy are applied to adapter updates. The implementation supports both low-memory GPU execution and multi-GPU client-parallel training on heterogeneous shared hardware. Comparative experiments on the present setup across multiple training and aggregation conditions with PrivFedTalk, FedAvg, and FedProx show stable federated optimization and successful end-to-end training and evaluation under constrained resources. The results support the feasibility of privacy-aware personalized talking-head training in federated environments, while suggesting that stronger component-wise, privacy-utility, and qualitative claims need further standardized evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2604_08037
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PrivFedTalk: Privacy-Aware Federated Diffusion with Identity-Stable Adapters for Personalized Talking-Head Generation
Mazumdar, Soumya
Rakesh, Vineet Kumar
Samanta, Tapas
Cryptography and Security
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Talking-head generation has advanced rapidly with diffusion-based generative models, but training usually depends on centralized face-video and speech datasets, raising major privacy concerns. The problem is more acute for personalized talking-head generation, where identity-specific data are highly sensitive and often cannot be pooled across users or devices. PrivFedTalk is presented as a privacy-aware federated framework for personalized talking-head generation that combines conditional latent diffusion with parameter-efficient identity adaptation. A shared diffusion backbone is trained across clients, while each client learns lightweight LoRA identity adapters from local private audio-visual data, avoiding raw data sharing and reducing communication cost. To address heterogeneous client distributions, Identity-Stable Federated Aggregation (ISFA) weights client updates using privacy-safe scalar reliability signals computed from on-device identity consistency and temporal stability estimates. Temporal-Denoising Consistency (TDC) regularization is introduced to reduce inter-frame drift, flicker, and identity drift during federated denoising. To limit update-side privacy risk, secure aggregation and client-level differential privacy are applied to adapter updates. The implementation supports both low-memory GPU execution and multi-GPU client-parallel training on heterogeneous shared hardware. Comparative experiments on the present setup across multiple training and aggregation conditions with PrivFedTalk, FedAvg, and FedProx show stable federated optimization and successful end-to-end training and evaluation under constrained resources. The results support the feasibility of privacy-aware personalized talking-head training in federated environments, while suggesting that stronger component-wise, privacy-utility, and qualitative claims need further standardized evaluation.
title PrivFedTalk: Privacy-Aware Federated Diffusion with Identity-Stable Adapters for Personalized Talking-Head Generation
topic Cryptography and Security
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2604.08037