Journal of Grid Computing Программное обеспечение

LightCam: Lightweight Secure Collaborative Learning and Resource-Aware Aggregation in Camera Networks

Li, Ying, Tian, Maozeng, Wang, Qianyi, Yao, Bingxin, Cui, Xianghui, Sun, Pengxuan
Springer Nature · 2026-05-30 · DOI 10.1007/s10723-026-09835-8

Аннотация

LightCam is a lightweight, privacy-preserving federated learning framework for resource-constrained camera networks in smart city surveillance. It targets three key challenges: strict protection of identity-bearing video and audio, limited computation and bandwidth at edge cameras, and heterogeneous data and system conditions. LightCam decomposes a multimodal model into a frozen backbone and a small task head, so cameras only train and upload the head, greatly reducing local cost and exposure of shallow features. Local data are split into non-sensitive anchor samples and privacy-critical samples; DP-SGD is applied only to the private subset with a scene-aware dynamic privacy budget. A resource-aware aggregation mechanism further weights client updates by data volume, update stability, and device status. Experiments on a multimodal benchmark constructed from CelebA, CIFAR-10, and UrbanSound8K show that LightCam achieves 85.82% accuracy under a strict total privacy budget ( $$\varepsilon =2.0$$ ε = 2.0 ), while reducing per-round communication by over two orders of magnitude and maintaining stable convergence under heterogeneous and impaired clients.

Читать у издателя →