Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.15102 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918062293254144 |
|---|---|
| author | Peng, Shizhao Li, Shoumo Tao, Tianle |
| author_facet | Peng, Shizhao Li, Shoumo Tao, Tianle |
| contents | Privacy-preserving neural network training in vertically partitioned scenarios is vital for secure collaborative modeling across institutions. This paper presents \textbf{EVA-S2PMLP}, an Efficient, Verifiable, and Accurate Secure Two-Party Multi-Layer Perceptron framework that introduces spatial-scale optimization for enhanced privacy and performance. To enable reliable computation under real-number domain, EVA-S2PMLP proposes a secure transformation pipeline that maps scalar inputs to vector and matrix spaces while preserving correctness. The framework includes a suite of atomic protocols for linear and non-linear secure computations, with modular support for secure activation, matrix-vector operations, and loss evaluation. Theoretical analysis confirms the reliability, security, and asymptotic complexity of each protocol. Extensive experiments show that EVA-S2PMLP achieves high inference accuracy and significantly reduced communication overhead, with up to $12.3\times$ improvement over baselines. Evaluation on benchmark datasets demonstrates that the framework maintains model utility while ensuring strict data confidentiality, making it a practical solution for privacy-preserving neural network training in finance, healthcare, and cross-organizational AI applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_15102 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EVA-S2PMLP: Secure and Scalable Two-Party MLP via Spatial Transformation Peng, Shizhao Li, Shoumo Tao, Tianle Cryptography and Security Information Theory Privacy-preserving neural network training in vertically partitioned scenarios is vital for secure collaborative modeling across institutions. This paper presents \textbf{EVA-S2PMLP}, an Efficient, Verifiable, and Accurate Secure Two-Party Multi-Layer Perceptron framework that introduces spatial-scale optimization for enhanced privacy and performance. To enable reliable computation under real-number domain, EVA-S2PMLP proposes a secure transformation pipeline that maps scalar inputs to vector and matrix spaces while preserving correctness. The framework includes a suite of atomic protocols for linear and non-linear secure computations, with modular support for secure activation, matrix-vector operations, and loss evaluation. Theoretical analysis confirms the reliability, security, and asymptotic complexity of each protocol. Extensive experiments show that EVA-S2PMLP achieves high inference accuracy and significantly reduced communication overhead, with up to $12.3\times$ improvement over baselines. Evaluation on benchmark datasets demonstrates that the framework maintains model utility while ensuring strict data confidentiality, making it a practical solution for privacy-preserving neural network training in finance, healthcare, and cross-organizational AI applications. |
| title | EVA-S2PMLP: Secure and Scalable Two-Party MLP via Spatial Transformation |
| topic | Cryptography and Security Information Theory |
| url | https://arxiv.org/abs/2506.15102 |