Scholarlink

<p>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 (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\varepsilon =2.0\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mi>ε</mi> <mo>=</mo> <mn>2.0</mn> </mrow> </math></EquationSource> </InlineEquation>), while reducing per-round communication by over two orders of magnitude and maintaining stable convergence under heterogeneous and impaired clients.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

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

  • 期刊论文

  • 发表日期：

    2026年5月30日

查看全文
  • Ying Li,
  • Maozeng Tian,
  • Qianyi Wang,
  • Bingxin Yao,
  • Xianghui Cui,
  • Pengxuan Sun

摘要

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.