Skip to content

Encryptability As a Coordinate Choice: Depth-One Homomorphic Federated Learning of Quantum Neural Networks

Sep 2026 · 0 citations · 50 references
Physics Computer Science

TL;DR

Leveraging this reduction yields a non-interactive protocol for encrypted federated training of hybrid quantum--classical networks, which includes correctness proofs for aggregation and sign handling, plus a compilation lemma proving parameterised entanglers add only constant-factor overhead without altering the depth class.

Abstract

Encrypted training relies on keeping server-side updates low-degree. This constraint traditionally excludes models whose weights inhabit a compact Lie group (notably variational quantum circuits, where every trainable weight is an $\mathrm{SU(2)}$ rotation). Expressed in Euler angles or discrete alphabets, these updates appear transcendental, historically demanding prohibitive costs: one client--server round per gate, or upwards of $25{,}000$ operations per weight. This penalty is strictly an artefact of coordinates. In the unit-quaternion (spin) chart, group composition is exactly bilinear (degree two, with coefficients in $\{-1,0,+1\}$). Consequently, encrypted rotation updates cost one multiplicative level and federated averaging costs zero in any levelled homomorphic scheme, completely eliminating bootstrapping. This implementation-independent algebraic property is confirmed across two cryptographic backends, introducing only $0.0$ and $-2.0\times10^{-12}$ rad of aggregation error. Leveraging this reduction yields a non-interactive protocol for encrypted federated training of hybrid quantum--classical networks. It includes correctness proofs for aggregation and sign handling, plus a compilation lemma proving parameterised entanglers add only constant-factor overhead without altering the depth class. Empirically, a paired five-seed study confirms zero measurable utility tax ($\Delta=+9\times10^{-6}$ MSE, $p=0.92$), and a noise-budget ablation falsifies the hypothesis that encryption noise regularises. These convergence trends replicate across datasets and scale to $20$ clients. Finally, hardware validation on a $156$-qubit processor achieves $0.9918$ fidelity against a $0.99957$ unencrypted control.

View source

Similar papers

Preprint Oct 2026

Classical Verification of a Remote Quantum Processor via Degenerate Concordant Computations: An Application to Randomness Generation

A client who rents a cloud quantum processor cannot easily tell whether the bitstrings it receives came from a quantum device. Certification by random circuit sampling runs on present hardware, but scoring each returned sample costs the client time $O(2^n)$. We give a protocol in which the client scores each round in t...

Bishal Kumar Das, L. Priyadarshi · 1 citation
#machine learning Preprint Oct 2026

Where Quantum Fourier Sampling Stops Short: A Three-Gate Audit Protocol for Delay-PUF Security Models

Quantum Fourier sampling may help audit the spectral learnability of delay-based physical unclonable functions (PUFs). We ask whether that promise survives access matching, a strong classical comparator, and oracle synthesis. Three gates structure the evaluation. Structure: low degree is not small support at reachable...

Owen Friedewald, Ali Shiri Sichani, Chi-Ren Shyu · 0 citations
Open access Aug 2026

EHEIR: Efficient Homomorphic Encrypted Inference via Architectural Redesign

This work presents a framework that reformulates HE-aware model design as a constrained neural architecture search problem, where the objective is to identify architectures that are both cryptographically feasible and computationally efficient while preserving task performance.

Reeshav Chowdhury, Anoop Mishra, Deepak Khazanchi et al. · 0 citations
Preprint Oct 2026

How to Build Pseudorandom Unitaries in Microcrypt

We provide the first evidence relative to a classical oracle that pseudorandom unitaries (PRUs) can exist without quantum-computable one-way functions. To obtain this result, we first prove that five independent random diagonal phase layers interleaved with Hadamard transforms \[ U=F_5HF_4HF_3HF_2HF_1 \] form a strong...

Aditya Gulati, Dakshita Khurana, Kabir Tomer · 0 citations
Preprint Sep 2026

Exponential lower bounds for low-degree strategies in position-based quantum cryptography

Non-local quantum computation (NLQC) consists on the implementation of a bipartite unitary $U_{AB}$ by two cooperating distant players by means of a two-round protocol with a single intermediate round of simultaneous communication. It is a major open question to know whether there exists a unitary $U_{AB}$ whose implem...

Isabel M. Moreno-Cuadrado, David Pérez-García, C. Palazuelos · 1 citation
Sep 2026

Shuffling is Not Enough: Breaking Permutation-Based Model Confidentiality in Hybrid FHE Inference

It is shown that input DP is orthogonal to model confidentiality and that the local-DP premise required for shuffle amplification cannot hold under correctness-bounded noise, and that the leaked spectra enable fingerprinting, lineage attribution, and improved logit-based extraction, while suppressing them destroys infe...

Jiseung Kim, Hyung Tae Lee · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

Microsoft Research Blog Nov 3, 2026

Learn the rules: The hacker mindset

Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.

MIT News · Artificial Intelligence Oct 28, 2026

Making machines that can listen

Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.