| Title | VESTA: A Secure and Efficient FHE-based Three-Party Vectorized Evaluation System for Tree Aggregation Models |
| Creator | |
| Date Issued | 2025-03-10 |
| Source Publication | Proceedings of the ACM on Measurement and Analysis of Computing Systems
 |
| Volume | 9Issue:1 |
| Abstract | Machine Learning as a Service (MLaaS) platforms simplify the development of machine learning applications across multiple parties. However, the model owner, compute server, and client user may not trust each other, creating a need for privacy-preserving approaches that allow applications to run without revealing proprietary data. In this work, we focus on a widely used classical machine learning model - tree ensembles. While previous efforts have applied Fully Homomorphic Encryption (FHE) to this model, these solutions suffer from slow inference speeds and excessive memory consumption. To address these issues, we propose VESTA, which includes a compiler and a runtime to reduce tree evaluation time and memory usage. VESTA includes two key techniques: First, VESTA precomputes a portion of the expensive FHE operations at compile-time, improving inference speed. Second, VESTA uses a partitioning pass in its compiler to divide the ensemble model into sub-models, enabling task-level parallelism. Comprehensive evaluation shows that VESTA achieves a 2.1× speedup and reduces memory consumption by 59.4% compared to the state-of-the-art. |
| Keyword | domain-specific compiler homomorphic encryption parallelism tree ensembles vectorization |
| DOI | 10.1145/3711707 |
| URL | View source |
| Language | 英语English |
| Scopus ID | 2-s2.0-105003217810 |
| Citation statistics | |
| Document Type | Journal article |
| Identifier | http://repository.uic.edu.cn/handle/39GCC9TT/12817 |
| Collection | Beijing Normal-Hong Kong Baptist University |
| Corresponding Author | Liu，Hongyuan |
| Affiliation | 1.The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China 2.Guangdong Provincial/Zhuhai Key Laboratory of IRADS,BNU-HKBU United International College,Zhuhai,China 3.Hong Kong Baptist University,Hong Kong,Hong Kong 4.School of Cyber Science and Technology,Shandong University,Qingdao,China 5.Stevens Institute of Technology,United States |
| Recommended Citation GB/T 7714 | Zhao，Haosong,Huang，Junhao,Chen，Zihanget al. VESTA: A Secure and Efficient FHE-based Three-Party Vectorized Evaluation System for Tree Aggregation Models[J]. Proceedings of the ACM on Measurement and Analysis of Computing Systems, 2025, 9(1). |
| APA | Zhao，Haosong., Huang，Junhao., Chen，Zihang., Zhu，Kunxiong., Chen，Donglong., .. & Liu，Hongyuan. (2025). VESTA: A Secure and Efficient FHE-based Three-Party Vectorized Evaluation System for Tree Aggregation Models. Proceedings of the ACM on Measurement and Analysis of Computing Systems, 9(1). |
| MLA | Zhao，Haosong,et al."VESTA: A Secure and Efficient FHE-based Three-Party Vectorized Evaluation System for Tree Aggregation Models". Proceedings of the ACM on Measurement and Analysis of Computing Systems 9.1(2025). |
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
BNBU 
Library
Edit Comment