SoK: Can Fully Homomorphic Encryption Support General AI Computation? A Functional and Cost Analysis
Authors: Jiaqi Xue (University of Central Florida), Xin Xin (University of Central Florida), Wei Zhang (University of Central Florida), Mengxin Zheng (University of Central Florida), Qianqian Song (University of Florida), Minxuan Zhou (Illinois Institute of Technology), Yushun Dong (Florida State University), Dongjie Wang (The University of Kansas), Xun Chen (Samsung Research America), Jiafeng Xie (Villanova University), Liqiang Wang (University of Central Florida), David Mohaisen (University of Central Florida), Hongyi Wu (University of Arizona), Qian Lou (University of Central Florida)
Volume: 2026
Issue: 2
Pages: 680–696
DOI: https://doi.org/10.56553/popets-2026-0066
Abstract: Artificial intelligence (AI) increasingly powers sensitive applications in domains such as healthcare and finance, relying on both extit{linear operations} (e.g., matrix multiplications in large language models) and extit{non-linear operations} (e.g., sorting in retrieval-augmented generation). Fully homomorphic encryption (FHE) has emerged as a promising tool for privacy-preserving computation, but it remains unclear whether existing methods can support the full spectrum of AI workloads that combine these operations. In this SoK, we ask: extit{Can FHE support general AI computation?} We provide both a functional analysis and a cost analysis. First, we categorize ten distinct FHE approaches and evaluate their ability to support general computation. We then identify three promising candidates and benchmark workloads that mix linear and non-linear operations across different bit lengths and SIMD parallelization settings. Finally, we evaluate five real-world, privacy-sensitive AI applications that instantiate these workloads. Our results quantify the costs of achieving general computation in FHE and offer practical guidance on selecting FHE methods that best fit specific AI application requirements. Our codes are available at https://github.com/UCF-ML-Research/FHE-AI-Generality.
Keywords: Fully Homomorphic Encryption, Generality Measurement
Copyright in PoPETs articles are held by their authors. This article is published under a Creative Commons Attribution 4.0 license.
