FedVideoMAE: Efficient Privacy-Preserving Federated Video Moderation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Tao, Ziyuan, Xu, Chuanzhi, Jayawardana, Sandaru, Mahmood, Adnan, Bao, Wei, Thilakarathna, Kanchana, Lim, Teng Joon
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918425978208256
author Tao, Ziyuan
Xu, Chuanzhi
Jayawardana, Sandaru
Mahmood, Adnan
Bao, Wei
Thilakarathna, Kanchana
Lim, Teng Joon
author_facet Tao, Ziyuan
Xu, Chuanzhi
Jayawardana, Sandaru
Mahmood, Adnan
Bao, Wei
Thilakarathna, Kanchana
Lim, Teng Joon
contents Short-form video moderation increasingly needs learning pipelines that protect user privacy without paying the full bandwidth and latency cost of cloud-centralized inference. We present FedVideoMAE, an on-device federated framework for video violence detection that combines self-supervised VideoMAE representations, LoRA-based parameter-efficient adaptation, client-side DP-SGD, and server-side secure aggregation. By updating only 5.5M parameters (about 3.5% of a 156M backbone), FedVideoMAE reduces communication by 28.3x relative to full-model federated updates while keeping raw videos on device throughout training. On RWF-2000 with 40 clients, the method reaches 77.25% accuracy without privacy protection and 65~66% under strong differential privacy. We further show that this privacy gap is consistent with an effective-SNR analysis tailored to the small-data, parameter-efficient federated regime, which indicates roughly 8.5~12x DP-noise amplification in our setting. To situate these results more clearly, we also compare against archived full-model federated baselines and summarize auxiliary transfer behavior on RLVS and binary UCF-Crime. Taken together, these findings position FedVideoMAE as a practical operating point for privacy-preserving video moderation on edge devices. Our code can be found at: https://github.com/zyt-599/FedVideoMAE.
format Preprint
id arxiv_https___arxiv_org_abs_2512_18809
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FedVideoMAE: Efficient Privacy-Preserving Federated Video Moderation
Tao, Ziyuan
Xu, Chuanzhi
Jayawardana, Sandaru
Mahmood, Adnan
Bao, Wei
Thilakarathna, Kanchana
Lim, Teng Joon
Computer Vision and Pattern Recognition
Artificial Intelligence
Multimedia
Short-form video moderation increasingly needs learning pipelines that protect user privacy without paying the full bandwidth and latency cost of cloud-centralized inference. We present FedVideoMAE, an on-device federated framework for video violence detection that combines self-supervised VideoMAE representations, LoRA-based parameter-efficient adaptation, client-side DP-SGD, and server-side secure aggregation. By updating only 5.5M parameters (about 3.5% of a 156M backbone), FedVideoMAE reduces communication by 28.3x relative to full-model federated updates while keeping raw videos on device throughout training. On RWF-2000 with 40 clients, the method reaches 77.25% accuracy without privacy protection and 65~66% under strong differential privacy. We further show that this privacy gap is consistent with an effective-SNR analysis tailored to the small-data, parameter-efficient federated regime, which indicates roughly 8.5~12x DP-noise amplification in our setting. To situate these results more clearly, we also compare against archived full-model federated baselines and summarize auxiliary transfer behavior on RLVS and binary UCF-Crime. Taken together, these findings position FedVideoMAE as a practical operating point for privacy-preserving video moderation on edge devices. Our code can be found at: https://github.com/zyt-599/FedVideoMAE.
title FedVideoMAE: Efficient Privacy-Preserving Federated Video Moderation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Multimedia
url https://arxiv.org/abs/2512.18809