EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Merits of geometric algebra applied to cryptography and machine learning

David William Silva iD

Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences · 13.08.2026 · 384 (2326)

DOI: 10.1098/rsta.2025.0107 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, online erschienen am 13.08.2026. Verfasst von David William Silva. Beteiligte Einrichtung: DataHubz , Colorado Springs, CO, USA. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: DataHubz.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present Clifford fully homomorphic encryption (FHE), the first ring-learning with errors (RLWE)-based FHE scheme with native support for all Clifford algebra operations, enabling privacy-preserving computation on geometric data. Unlike conventional FHE schemes that flatten geometric structure into scalar operations, our approach maintains the algebraic properties of multi-vectors through homomorphic geometric products. Building on this foundation, we introduce geometric neural networks that operate directly on encrypted multi-vectors, achieving the first-ever demonstration of privacy-preserving geometric deep learning. Our construction encrypts three-dimensional point clouds as Cl(3,0) multi-vectors and performs encrypted classification with less than 1% accuracy loss compared to plaintext, completing inference in under 60 s. These results demonstrate that geometric algebra (GA) provides unique advantages for both cryptographic constructions (enabling structure-preserving encryption) and machine learning (ML) (enabling privacy-preserving geometric learning), opening new pathways at the intersection of cryptography, ML and applied mathematics. This article is part of the theme issue ‘Modern applications of geometric algebra’.

Schlagwörter

Stichwörter der Autor:innen

CKKSClifford algebrageometric algebrageometric neural networkshomomorphic encryptionprivacy-preserving machine learningthree-dimensional point cloud classification

Autor:innen und Institutionen

  • DataHubz , Colorado Springs, CO, USA.

ORCID-Profile: David William Silva

Förderung

  • DataHubz

Zitieren

APA

Silva, D. W. (2026). Merits of geometric algebra applied to cryptography and machine learning. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 384(2326). https://doi.org/10.1098/rsta.2025.0107

Vancouver

Silva DW. Merits of geometric algebra applied to cryptography and machine learning. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences. 2026;384(2326). doi:10.1098/rsta.2025.0107

BibTeX
@article{Silva2026,
  author = {Silva, David William},
  title = {Merits of geometric algebra applied to cryptography and machine learning},
  journal = {Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences},
  year = {2026},
  volume = {384},
  number = {2326},
  doi = {10.1098/rsta.2025.0107}
}
Kostenlos starten →