Skip to content

Federated Learning with Quantum Computing and Fully Homomorphic Encryption: A Novel Computing Paradigm Shift in Privacy-Preserving ML

Authors: Siddhant Dutta; Pavana P Karanth; Pedro Maciel Xavier; Iago Leal de Freitas; Nouhaila Innan; Sadok Ben Yahia; Muhammad Shafique; David E. Bernal Neira
Year: 2024
Venue: arXiv preprint

type: application collection: ppml status: auto

Links: arXiv:2409.11430

Summary

Auto-extracted summary (unreviewed)

This preprint argues that emerging computing paradigms (analog, quantum, specialized digital hardware) can host privacy-preserving ML, and instantiates the idea by applying fully homomorphic encryption to a federated-learning neural network that mixes classical and quantum layers. The excerpt contains only the abstract and introduction, so no quantitative results are available; the code is released on GitHub.

Abstract

The widespread deployment of products powered by machine learning models is raising concerns around data privacy and information security worldwide. To address this issue, Federated Learning was first proposed as a privacy-preserving alternative to conventional methods that allow multiple learning clients to share model knowledge without disclosing private data. A complementary approach known as Fully Homomorphic Encryption (FHE) is a quantum-safe cryptographic system that enables operations to be performed on encrypted weights. However, implementing mechanisms such as these in practice often comes with significant computational overhead and can expose potential security threats. Novel computing paradigms, such as analog, quantum, and specialized digital hardware, present opportunities for implementing privacy-preserving machine learning systems while enhancing security and mitigating performance loss. This work instantiates these ideas by applying the FHE scheme to a Federated Learning Neural Network architecture that integrates both classical and quantum layers.
Source: arxiv

Extracted details

Field Value Source Confidence
contribution FHE-protected federated learning with a hybrid classical-quantum neural network llm 0.50
contribution discussion of novel computing paradigms for privacy-preserving ML llm 0.50
contribution open-source implementation llm 0.50
schemes FHE (scheme not stated in excerpt) llm 0.50
models hybrid classical-quantum neural network llm 0.50
tasks federated learning llm 0.50
tasks quantum machine learning llm 0.50
interaction non-interactive FHE llm 0.50
code url https://github.com/elucidator8918/QFL-MLNCP-NeurIPS.6 (URL found in the full text) regex 0.50
code url https://github.com/elucidator8918/QFL-MLNCP-NeurIPS llm 0.50
limitations FHE and FL incur significant computational overhead (stated in general terms) llm 0.50
llm relevance low llm 0.50

Keyword mentions

Counts of vocabulary terms in the full text (first page of occurrence in brackets).

  • model: SVM 1 [p.9]
  • dataset: CIFAR-10 5 [p.5]
  • technique: Federated learning 28 [p.1], Rotations 3 [p.4], Quantization 3 [p.4]
  • assumption: Post-quantum 3 [p.1]
  • task: Medical / healthcare 10 [p.3], IoT / edge 4 [p.3], Finance 2 [p.3]
  • topic: Homomorphic encryption 36 [p.1]

Files

Path (under papers/) Collection Pages Size SHA-256 Note
references/ppml/federated-learning/dutta-2024_federated-learning-with-quantum-computing-and-fhe.pdf ppml/federated-learning 10 347.1 KB cdd41e0a81a8 was Dutta et al. - 2024 - Federated Learning with Quantum Computing and Fully Homomorphic Encryption A Novel Computing Paradi.pdf

Database key: federated-learning-with-quantum-computing-and-fully-homomorphic · created 2026-11-05 · updated 2026-11-05 · edit with python3 tools/paperdb.py set federated-learning-with-quantum-computing-and-fully-homomorphic COLUMN VALUE