{"ID":2826584,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.18809","arxiv_id":"2512.18809","title":"FedVideoMAE: Efficient Privacy-Preserving Federated Video Moderation","abstract":"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.","short_abstract":"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, LoR...","url_abs":"https://arxiv.org/abs/2512.18809","url_pdf":"https://arxiv.org/pdf/2512.18809v2","authors":"[\"Ziyuan Tao\",\"Chuanzhi Xu\",\"Sandaru Jayawardana\",\"Adnan Mahmood\",\"Wei Bao\",\"Kanchana Thilakarathna\",\"Teng Joon Lim\"]","published":"2025-12-21T17:01:44Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.MM\"]","methods":"[\"LoRA\"]","has_code":false,"code_links":[{"ID":605755,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2826584,"paper_url":"https://arxiv.org/abs/2512.18809","paper_title":"FedVideoMAE: Efficient Privacy-Preserving Federated Video Moderation","repo_url":"https://github.com/zyt-599/FedVideoMAE","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}