CONFIDENTIAL TRAINING AND INFERENCE USING SECURE MULTI-PARTY COMPUTATION ON VERTICALLY PARTITIONED DATASET
- Title
- CONFIDENTIAL TRAINING AND INFERENCE USING SECURE MULTI-PARTY COMPUTATION ON VERTICALLY PARTITIONED DATASET
- Creator
- Tiwari K.; Sarkar N.; George J.P.
- Description
- Digitalization across all spheres of life has given rise to issues like data ownership and privacy. Privacy-Preserving Machine Learning (PPML), an active area of research, aims to preserve privacy for machine learning (ML) stakeholders like data owners, ML model owners, and inference users. The Paper, CoTraIn-VPD, proposes private ML inference and training of models for vertically partitioned datasets with Secure Multi-Party Computation (SPMC) and Differential Privacy (DP) techniques. The proposed approach addresses complications linked with the privacy of various ML stakeholders dealing with vertically portioned datasets. This technique is implemented in Python using open-source libraries such as SyMPC (SMPC functions), PyDP (DP aggregations), and CrypTen (secure and private training). The paper uses information privacy measures, including mutual information and KL-Divergence, across different privacy budgets to empirically demonstrate privacy preservation with high ML accuracy and minimal performance cost. 2023 SCPE.
- Source
- Scalable Computing, Vol-24, No. 4, pp. 1065-1076.
- Date
- 2023-01-01
- Publisher
- West University of Timisoara
- Subject
- Confidential Inference; Differential Privacy (DP); Privacy-Preserving Machine Learning (PPML); Vertically Partitioned Datasets Secure Multi-Party Computation (SMPC)
- Coverage
- Tiwari K., Department of Computer Science, CHRIST University, India; Sarkar N., Department of Computer Science, CHRIST University, India; George J.P., Department of Computer Science, CHRIST University, India
- Rights
- All Open Access; Gold Open Access
- Relation
- ISSN: 18951767
- Format
- Online
- Language
- English
- Type
- Article
Collection
Citation
Tiwari K.; Sarkar N.; George J.P., “CONFIDENTIAL TRAINING AND INFERENCE USING SECURE MULTI-PARTY COMPUTATION ON VERTICALLY PARTITIONED DATASET,” CHRIST (Deemed To Be University) Institutional Repository, accessed February 24, 2025, https://archives.christuniversity.in/items/show/14500.