FHAIM: Fully Homomorphic AIM For Private Synthetic Data Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910016797147136 |
|---|---|
| author | Kumar, Mayank Lou, Qian Barreto, Paulo De Cock, Martine Pentyala, Sikha |
| author_facet | Kumar, Mayank Lou, Qian Barreto, Paulo De Cock, Martine Pentyala, Sikha |
| contents | Data is the lifeblood of AI, yet much of the most valuable data remains locked in silos due to privacy and regulations. As a result, AI remains heavily underutilized in many of the most important domains, including healthcare, education, and finance. Synthetic data generation (SDG), i.e. the generation of artificial data with a synthesizer trained on real data, offers an appealing solution to make data available while mitigating privacy concerns, however existing SDG-as-a-service workflow require data holders to trust providers with access to private data. We propose FHAIM, the first fully homomorphic encryption (FHE) framework for training a marginal-based synthetic data generator on encrypted tabular data. FHAIM adapts the widely used AIM algorithm to the FHE setting using novel FHE protocols, ensuring that the private data remains encrypted throughout and is released only with differential privacy guarantees. Our empirical analysis show that FHAIM preserves the performance of AIM while maintaining feasible runtimes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05838 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FHAIM: Fully Homomorphic AIM For Private Synthetic Data Generation Kumar, Mayank Lou, Qian Barreto, Paulo De Cock, Martine Pentyala, Sikha Cryptography and Security Artificial Intelligence Data is the lifeblood of AI, yet much of the most valuable data remains locked in silos due to privacy and regulations. As a result, AI remains heavily underutilized in many of the most important domains, including healthcare, education, and finance. Synthetic data generation (SDG), i.e. the generation of artificial data with a synthesizer trained on real data, offers an appealing solution to make data available while mitigating privacy concerns, however existing SDG-as-a-service workflow require data holders to trust providers with access to private data. We propose FHAIM, the first fully homomorphic encryption (FHE) framework for training a marginal-based synthetic data generator on encrypted tabular data. FHAIM adapts the widely used AIM algorithm to the FHE setting using novel FHE protocols, ensuring that the private data remains encrypted throughout and is released only with differential privacy guarantees. Our empirical analysis show that FHAIM preserves the performance of AIM while maintaining feasible runtimes. |
| title | FHAIM: Fully Homomorphic AIM For Private Synthetic Data Generation |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2602.05838 |