Affiliation:
1. MOE Key Lab of HCST, Dept of Computer Science, School of EECS, Peking University, Beijing, China
2. Microsoft Research, Beijing, China
Abstract
Deep learning models have been deployed to a wide range of edge devices. Since the data distribution on edge devices may differ from the cloud where the model was trained, it is typically desirable to customize the model for each edge device to improve accuracy. However, such customization is hard because collecting data from edge devices is usually prohibited due to privacy concerns. In this paper, we propose PMC, a privacy-preserving model customization framework to effectively customize a CNN model from the cloud to edge devices without collecting raw data. Instead, we introduce a method to extract statistical information from the edge, which contains adequate domain-related knowledge for model customization. PMC uses Gaussian distribution parameters to describe the edge data distribution, reweights the cloud data based on the parameters, and uses the reweighted data to train a specialized model for the edge device. During this process, differential privacy can be enforced by adding computed noises to the Gaussian parameters. Experiments on public datasets show that PMC can improve model accuracy by a large margin through customization. Finally, a study on user-generated data demonstrates the effectiveness of PMC in real-world settings.
Funder
National Natural Science Foundation of China
National Key Research and Development Program of China
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Networks and Communications,Hardware and Architecture,Human-Computer Interaction
Reference62 articles.
1. Deep Learning with Differential Privacy
2. Apple. [n.d.]. Differential Privacy Overview. https://www.apple.com/privacy/docs/Differential_Privacy_Overview.pdf. Apple. [n.d.]. Differential Privacy Overview. https://www.apple.com/privacy/docs/Differential_Privacy_Overview.pdf.
3. Apple. [n.d.]. Private on-device technologies to browse and edit photos and videos on iOS and iPadOS. https://www.apple.com/ios/photos/pdf/Photos_Tech_Brief_Sept_2019.pdf. Apple. [n.d.]. Private on-device technologies to browse and edit photos and videos on iOS and iPadOS. https://www.apple.com/ios/photos/pdf/Photos_Tech_Brief_Sept_2019.pdf.
4. MoRePriv
Cited by
38 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Spatial-Temporal Masked Autoencoder for Multi-Device Wearable Human Activity Recognition;Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies;2023-12-19
2. Human Movement Recognition Based on 3D Point Cloud Spatiotemporal Information from Millimeter-Wave Radar;Sensors;2023-11-27
3. AccessWear: Making Smartphone Applications Accessible to Blind Users;Proceedings of the 29th Annual International Conference on Mobile Computing and Networking;2023-10-02
4. Towards Generalized mmWave-based Human Pose Estimation through Signal Augmentation;Proceedings of the 29th Annual International Conference on Mobile Computing and Networking;2023-10-02
5. Practically Adopting Human Activity Recognition;Proceedings of the 29th Annual International Conference on Mobile Computing and Networking;2023-10-02