Privacy-Preserving Federated Action Recognition via Differentially Private Selective Tuning and Efficient Communication

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zakariyya, Idris, Ng, Pai Chet, Sivangi, Kaushik Bhargav, Sheikholeslami, S. Mohammad, Plataniotis, Konstantinos N., Deligianni, Fani
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908905755377664
author Zakariyya, Idris
Ng, Pai Chet
Sivangi, Kaushik Bhargav
Sheikholeslami, S. Mohammad
Plataniotis, Konstantinos N.
Deligianni, Fani
author_facet Zakariyya, Idris
Ng, Pai Chet
Sivangi, Kaushik Bhargav
Sheikholeslami, S. Mohammad
Plataniotis, Konstantinos N.
Deligianni, Fani
contents Federated video action recognition enables collaborative model training without sharing raw video data, yet remains vulnerable to two key challenges: \textit{model exposure} and \textit{communication overhead}. Gradients exchanged between clients and the server can leak private motion patterns, while full-model synchronization of high-dimensional video networks causes significant bandwidth and communication costs. To address these issues, we propose \textit{Federated Differential Privacy with Selective Tuning and Efficient Communication for Action Recognition}, namely \textit{FedDP-STECAR}. Our \textit{FedDP-STECAR} framework selectively fine-tunes and perturbs only a small subset of task-relevant layers under Differential Privacy (DP), reducing the surface of information leakage while preserving temporal coherence in video features. By transmitting only the tuned layers during aggregation, communication traffic is reduced by over 99\% compared to full-model updates. Experiments on the UCF-101 dataset using the MViT-B-16x4 transformer show that \textit{FedDP-STECAR} achieves up to \textbf{70.2\% higher accuracy} under strict privacy ($ε=0.65$) in centralized settings and \textbf{48\% faster training} with \textbf{73.1\% accuracy} in federated setups, enabling scalable and privacy-preserving video action recognition. Code available at https://github.com/izakariyya/mvit-federated-videodp
format Preprint
id arxiv_https___arxiv_org_abs_2603_21305
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Privacy-Preserving Federated Action Recognition via Differentially Private Selective Tuning and Efficient Communication
Zakariyya, Idris
Ng, Pai Chet
Sivangi, Kaushik Bhargav
Sheikholeslami, S. Mohammad
Plataniotis, Konstantinos N.
Deligianni, Fani
Computer Vision and Pattern Recognition
Federated video action recognition enables collaborative model training without sharing raw video data, yet remains vulnerable to two key challenges: \textit{model exposure} and \textit{communication overhead}. Gradients exchanged between clients and the server can leak private motion patterns, while full-model synchronization of high-dimensional video networks causes significant bandwidth and communication costs. To address these issues, we propose \textit{Federated Differential Privacy with Selective Tuning and Efficient Communication for Action Recognition}, namely \textit{FedDP-STECAR}. Our \textit{FedDP-STECAR} framework selectively fine-tunes and perturbs only a small subset of task-relevant layers under Differential Privacy (DP), reducing the surface of information leakage while preserving temporal coherence in video features. By transmitting only the tuned layers during aggregation, communication traffic is reduced by over 99\% compared to full-model updates. Experiments on the UCF-101 dataset using the MViT-B-16x4 transformer show that \textit{FedDP-STECAR} achieves up to \textbf{70.2\% higher accuracy} under strict privacy ($ε=0.65$) in centralized settings and \textbf{48\% faster training} with \textbf{73.1\% accuracy} in federated setups, enabling scalable and privacy-preserving video action recognition. Code available at https://github.com/izakariyya/mvit-federated-videodp
title Privacy-Preserving Federated Action Recognition via Differentially Private Selective Tuning and Efficient Communication
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.21305