Preserving Data Privacy during Neural Architecture Search for Edge AI Applications
Liang, Yichuan Hou, Shanjung Chiu, Shinwei Hung, Shihhao
Liang, Yichuan
Hou, Shanjung
Chiu, Shinwei
Hung, Shihhao
Supervisor
Department
Computer Science
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Neural Architecture Search (NAS) has become an important technique for finding efficient and accurate neural network models, especially for edge AI applications on power-constrained and specialized devices. NAS is typically done in the cloud, as edge devices do not possess the computing power to perform NAS, but revealing the actual dataset to the cloud causes privacy concerns. While homomorphic encryption (HE) can be used to preserve data privacy by uploading encrypted data, it results in high computational overhead for both the edge devices and cloud servers and reduced accuracy for nonlinear activation functions. This paper argues that functional encryption (FE) would be a good alternative to preserve data privacy during cloud-based NAS with significantly less overhead and better accuracy than HE. We present a system architecture for conducting NAS with FE and validate the argument with experiments and security analysis. On the server side, we use GPU to parallel the BSGS algorithm of the decryption operation After integrating FE into our framework and optimizing it, we utilized GPU parallel computation to accelerate decryption and improved performance by 3.5 times compared to the baseline design.
Citation
Y. C. Liang, S. J. Hou, S. W. Chiu, and S. H. Hung, “Preserving Data Privacy during Neural Architecture Search for Edge AI Applications,” 2024 Research in Adaptive and Convergent Systems - Proceedings of the 2024 International Conference on Research in Adaptive and Convergent Systems, RACS 2024, pp. 160–167, Oct. 2025, doi: 10.1145/3649601.3698738
Source
Proceedings of the International Conference on Research in Adaptive and Convergent Systems
Conference
2024 International Conference on Research in Adaptive and Convergent Systems, RACS 2024
Keywords
ACM proceedings, baby-step giant-step, data privacy, deep learning accelerator, functional encryption, GPU, neural architecture search
Subjects
Source
2024 International Conference on Research in Adaptive and Convergent Systems, RACS 2024
Publisher
Association for Computing Machinery