The Communication-Friendly Privacy-Preserving Machine Learning against Malicious Adversaries
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909389316685824 |
|---|---|
| author | Lu, Tianpei Zhang, Bingsheng Li, Lichun Ren, Kui |
| author_facet | Lu, Tianpei Zhang, Bingsheng Li, Lichun Ren, Kui |
| contents | With the increasing emphasis on privacy regulations, such as GDPR, protecting individual privacy and ensuring compliance have become critical concerns for both individuals and organizations. Privacy-preserving machine learning (PPML) is an innovative approach that allows for secure data analysis while safeguarding sensitive information. It enables organizations to extract valuable insights from data without compromising privacy. Secure multi-party computation (MPC) is a key tool in PPML, as it allows multiple parties to jointly compute functions without revealing their private inputs, making it essential in multi-server environments. We address the performance overhead of existing maliciously secure protocols, particularly in finite rings like $\mathbb{Z}_{2^\ell}$, by introducing an efficient protocol for secure linear function evaluation. We implement our maliciously secure MPC protocol on GPUs, significantly improving its efficiency and scalability. We extend the protocol to handle linear and non-linear layers, ensuring compatibility with a wide range of machine-learning models. Finally, we comprehensively evaluate machine learning models by integrating our protocol into the workflow, enabling secure and efficient inference across simple and complex models, such as convolutional neural networks (CNNs). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_09287 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Communication-Friendly Privacy-Preserving Machine Learning against Malicious Adversaries Lu, Tianpei Zhang, Bingsheng Li, Lichun Ren, Kui Cryptography and Security With the increasing emphasis on privacy regulations, such as GDPR, protecting individual privacy and ensuring compliance have become critical concerns for both individuals and organizations. Privacy-preserving machine learning (PPML) is an innovative approach that allows for secure data analysis while safeguarding sensitive information. It enables organizations to extract valuable insights from data without compromising privacy. Secure multi-party computation (MPC) is a key tool in PPML, as it allows multiple parties to jointly compute functions without revealing their private inputs, making it essential in multi-server environments. We address the performance overhead of existing maliciously secure protocols, particularly in finite rings like $\mathbb{Z}_{2^\ell}$, by introducing an efficient protocol for secure linear function evaluation. We implement our maliciously secure MPC protocol on GPUs, significantly improving its efficiency and scalability. We extend the protocol to handle linear and non-linear layers, ensuring compatibility with a wide range of machine-learning models. Finally, we comprehensively evaluate machine learning models by integrating our protocol into the workflow, enabling secure and efficient inference across simple and complex models, such as convolutional neural networks (CNNs). |
| title | The Communication-Friendly Privacy-Preserving Machine Learning against Malicious Adversaries |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2411.09287 |