[2603.20504] Meeting in the Middle: A Co-Design Paradigm for FHE and AI Inference

Computer Science > Cryptography and Security arXiv:2603.20504 (cs) [Submitted on 20 Mar 2026] Title:Meeting in the Middle: A Co-Design Paradigm for FHE and AI Inference Authors:Bernardo Magri, Benjamin Marsh, Paul Gebheim View a PDF of the paper titled Meeting in the Middle: A Co-Design Paradigm for FHE and AI Inference, by Bernardo Magri and Benjamin Marsh and Paul Gebheim View PDF HTML (experimental) Abstract:Modern cloud inference creates a two sided privacy problem where users reveal sensitive inputs to providers, while providers must execute proprietary model weights inside potentially leaky execution environments. Fully homomorphic encryption (FHE) offers cryptographic guarantees but remains prohibitively expensive for modern architectures. We argue that progress requires co-design where specializing FHE schemes/compilers for the static structure of inference circuits, while simultaneously constraining inference architectures to reduce dominant homomorphic cost drivers. We outline a meet in the middle agenda and concrete optimization targets on both axes. Comments: Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2603.20504 [cs.CR]   (or arXiv:2603.20504v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2603.20504 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Benjamin Marsh [view email] [v1] Fri, 20 Mar 2026 21:16:58 UTC (9 KB) Full-text links: Access Paper: View...