通过选择性微调与差分隐私，实现高效低泄漏的联邦视频动作识别。
Privacy-Preserving Federated Action Recognition via Differentially Private Selective Tuning and Efficient Communication
- 只对关键层进行微调并加噪，减少隐私泄露。
- 通信量降低99%以上，联邦设置下准确率达73.1%。
- 适合注重隐私与带宽限制的视频识别场景。
联邦视频动作识别可在不共享原始视频数据的情况下协同训练模型，但仍面临两大挑战：模型暴露和通信开销。客户端与服务器间交换的梯度可能泄露私有运动模式，而高维视频网络的全模型同步带来显著带宽和通信成本。为此，我们提出面向动作识别的差分隐私选择性微调与高效通信联邦框架（FedDP-STECAR）。该框架在差分隐私约束下，仅对少量任务相关层进行选择性微调与扰动，降低信息泄露面，同时保持视频特征的时间一致性。通过仅传输微调层进行聚合，通信流量相比全模型更新降低超过99%。在UCF-101数据集上使用MViT-B-16x4 Transformer进行实验表明，FedDP-STECAR在严格隐私保护（ε=0.65）的集中式设置下，准确率最高提升70.2%；在联邦设置中实现48%更快训练速度，达73.1%准确率，支持可扩展的隐私保护视频动作识别。代码已开源。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。