A Quantization-based Technique for Privacy Preserving Distributed Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913407011127296 |
|---|---|
| author | Colombo, Maurizio Asal, Rasool Damiani, Ernesto AlQassem, Lamees Mahmoud Almemari, Al Anoud Alhammadi, Yousof |
| author_facet | Colombo, Maurizio Asal, Rasool Damiani, Ernesto AlQassem, Lamees Mahmoud Almemari, Al Anoud Alhammadi, Yousof |
| contents | The massive deployment of Machine Learning (ML) models raises serious concerns about data protection. Privacy-enhancing technologies (PETs) offer a promising first step, but hard challenges persist in achieving confidentiality and differential privacy in distributed learning. In this paper, we describe a novel, regulation-compliant data protection technique for the distributed training of ML models, applicable throughout the ML life cycle regardless of the underlying ML architecture. Designed from the data owner's perspective, our method protects both training data and ML model parameters by employing a protocol based on a quantized multi-hash data representation Hash-Comb combined with randomization. The hyper-parameters of our scheme can be shared using standard Secure Multi-Party computation protocols. Our experimental results demonstrate the robustness and accuracy-preserving properties of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_19418 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Quantization-based Technique for Privacy Preserving Distributed Learning Colombo, Maurizio Asal, Rasool Damiani, Ernesto AlQassem, Lamees Mahmoud Almemari, Al Anoud Alhammadi, Yousof Cryptography and Security Artificial Intelligence The massive deployment of Machine Learning (ML) models raises serious concerns about data protection. Privacy-enhancing technologies (PETs) offer a promising first step, but hard challenges persist in achieving confidentiality and differential privacy in distributed learning. In this paper, we describe a novel, regulation-compliant data protection technique for the distributed training of ML models, applicable throughout the ML life cycle regardless of the underlying ML architecture. Designed from the data owner's perspective, our method protects both training data and ML model parameters by employing a protocol based on a quantized multi-hash data representation Hash-Comb combined with randomization. The hyper-parameters of our scheme can be shared using standard Secure Multi-Party computation protocols. Our experimental results demonstrate the robustness and accuracy-preserving properties of our approach. |
| title | A Quantization-based Technique for Privacy Preserving Distributed Learning |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2406.19418 |