FHAIM: Fully Homomorphic AIM For Private Synthetic Data Generation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 12 of its 31 references that are in the map. First posted on arXiv 5 Feb 2026.
Builds on
12 of 31 references.
References · 12
- 2021Winning the NIST Contest: A scalable and general approach to differentially private synthetic datacited by 101
- 2022AIM: An Adaptive and Iterative Mechanism for Differentially Private Synthetic Datacited by 88
- 2021Benchmarking Differentially Private Synthetic Data Generation Algorithmscited by 80
- 2019Graphical-model based estimation and inference for differential privacycited by 73
- 2023SoK: Privacy-Preserving Data Synthesiscited by 37
- 2022Private Synthetic Data for Multitask Learning and Marginal Queriescited by 35
- 2024Systematic Assessment of Tabular Data Synthesiscited by 17
- 2025Benchmarking Differentially Private Tabular Data Synthesiscited by 13
- 2024Privacy Vulnerabilities in Marginals-based Synthetic Datacited by 10
- 2023FLAIM: AIM-based Synthetic Data Generation in the Federated Settingcited by 6
- 2024CaPS: Collaborative and Private Synthetic Data Generation from Distributed Sourcescited by 4
- 2021Construction of Differentially Private Summaries over Fully Homomorphic Encryptioncited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.
- 2026RobPI: Robust Private Inference against Malicious Clientcited by 0
- 2026RobPI: Robust Private Inference against Malicious Client23 Feb 2026