UAV-assisted framework encrypts wireless computation with CKKS FHE
Original title: A Privacy-Preserving UAV-Assisted Secure Wireless Communication and Computing System Based on Fully Homomorphic Encryption
The design separates key distribution from encrypted aggregation, matrix multiplication, and decision-tree inference.
Authors propose a UAV-assisted framework combining CKKS fully homomorphic encryption with multi-party computation for beyond-5G wireless settings. UAVs decouple key distribution from encrypted computation, supporting encrypted weighted aggregation, matrix multiplication, and decision-tree inference. They report better time efficiency than BFV for decision trees and better time and space efficiency than BGV and SHE for matrix multiplication.
Unconfirmed: Efficiency and precision gains are reported only from the authors' experiments.
- The framework targets encrypted weighted aggregation, matrix multiplication, and decision-tree inference.
- For decision trees, the authors report floating-point support and better time efficiency than BFV.
- For aggregation, they report high numerical precision across varying data lengths.
From the original article
1 min read at arxiv.orgWith the advancement of beyond-5G networks, privacy-preserving communication and secure computation face critical challenges due to the openness of wireless channels. Existing security mechanisms protect data transmission but fail to secure the computation process itself.
By Quanxi Zhou · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.