Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.20504 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917355469144064 |
|---|---|
| author | Magri, Bernardo Marsh, Benjamin Gebheim, Paul |
| author_facet | Magri, Bernardo Marsh, Benjamin Gebheim, Paul |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_20504 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Meeting in the Middle: A Co-Design Paradigm for FHE and AI Inference Magri, Bernardo Marsh, Benjamin Gebheim, Paul Cryptography and Security Artificial Intelligence 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. |
| title | Meeting in the Middle: A Co-Design Paradigm for FHE and AI Inference |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2603.20504 |