# MOAI preprint reports 52.8% reduction in encrypted transformer evaluation time

_Published Wednesday, November 11, 2026 at 2:37 AM EST · AI, Science · Latest · Tier 2 — Notable_

Researchers propose MOAI, a framework for running transformer models on encrypted inputs, and report a 52.8% reduction in evaluation time compared with THOR, an existing non-interactive encrypted inference system. Homomorphic encryption lets a cloud provider compute on encrypted inputs, but its computational overhead remains a bottleneck.

MOAI arranges encrypted data consistently across layers to avoid format conversions and reduces costly operations called rotations. Its Softmax and LayerNorm algorithms eliminate 2,448 rotations in BERT-base inference. Applied to Powerformer, which simplifies those functions, MOAI reduces evaluation time by 55.7%. The preprint reports an amortized time of 2.36 minutes per input in a single GPU environment; the implementation is open source.

## Sources

- [cs.CR updates on arXiv.org](https://arxiv.org/abs/2611.13641)

---
Canonical: https://techandbusiness.org/newswire/7Lo5C1-J6EBvHYQyr5RBkG
Published: 2026-11-11T07:37:30.017Z
Story chronology: 2026-11-11T05:00:00.000Z
Retrieved: 2026-11-11T09:29:24.528Z
Publisher: Tech & Business (techandbusiness.org)