Efficient differentially private kernel support vector classifier for multi-class classification
- Authors
- Park, Jinseong; Byun, Junyoung; Choi, Yujin; Lee, Jaewook; Park, Saerom
- Issue Date
- Jan-2023
- Publisher
- ELSEVIER SCIENCE INC
- Keywords
- Differential privacy; Kernel method; Support vector data description; Support vector machine
- Citation
- INFORMATION SCIENCES, v.619, pp 889 - 907
- Pages
- 19
- Journal Title
- INFORMATION SCIENCES
- Volume
- 619
- Start Page
- 889
- End Page
- 907
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/71995
- DOI
- 10.1016/j.ins.2022.10.075
- ISSN
- 0020-0255
1872-6291
- Abstract
- In this paper, we propose a multi-class classification method using kernel supports and a dynamical system under differential privacy. For small datasets, kernel methods, such as kernel support vector machines (SVMs), show good generalization performance with high-dimensional feature mapping. However, kernel SVMs have a fundamental weakness in achieving differential privacy because they construct decision functions based on a subset of the training data called support vectors. Furthermore, multi-class SVMs must decompose the training data into a binary class, which requires multiple accesses to the same training data. To address these limitations, we develop a two-phase classification algorithm based on support vector data description (SVDD). We first generate and prove a differentially private SVDD (DP-SVDD) by perturbing the sphere center in a high-dimensional feature space. Next, we partition the input space using a dynamical system and classify the partitioned regions using a noisy count. The proposed method results in robust, fast, and user-friendly multi-class classification, even on small-sized datasets, where differential privacy performs poorly.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/71995)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.