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.

翻译：短视频审核日益需要能够保护用户隐私的学习流水线，同时避免云集中式推理带来的带宽和延迟成本。我们提出了FedVideoMAE——一个用于视频暴力检测的设备端联邦框架，该框架结合了自监督VideoMAE表示、基于LoRA的参数高效适配、客户端DP-SGD以及服务端安全聚合。通过仅更新5.5M参数（约为156M骨干网络的3.5%），FedVideoMAE相比全模型联邦更新将通信量降低28.3倍，同时在整个训练过程中保持原始视频存储在设备端。在包含40个客户端的RWF-2000数据集上，该方法在无隐私保护下达到77.25%的准确率，在强差分隐私下达到65%至66%。我们进一步表明，该隐私差距与针对小数据、参数高效联邦场景定制的有效信噪比分析结果一致，该分析表明在我们的设置中DP噪声放大约为8.5至12倍。为更清晰地定位这些结果，我们还对比了存档的全模型联邦基线，并总结了在RLVS和二元UCF-Crime上的辅助迁移行为。综合来看，这些发现将FedVideoMAE定位为边缘设备上实现隐私保护视频审核的一个实用工作点。我们的代码可在：https://github.com/zyt-599/FedVideoMAE 获取。