A Survey on Privacy-Preserving Machine Learning with Fully Homomorphic Encryption¶
Authors: Luis Bernardo Pulido-Gaytan; Andrei Tchernykh; Jorge M. Cortés-Mendoza; Mikhail Babenko; Gleb Radchenko
Year: 2021
Venue: Communications in Computer and Information Science
type: survey collection: ppml status: auto
Links: DOI
Summary¶
Auto-extracted summary (unreviewed)
This CARLA 2020 survey reviews fully homomorphic encryption as a tool for securely processing private data in the cloud, covering theoretical concepts, state of the art, limitations, potential applications and development tools such as SEAL and PALISADE. It then examines the intersection of FHE and machine learning from theoretical and practical viewpoints and identifies research directions for Machine Learning as a Service, positioning itself as a reference guide for researchers and practitioners.
Abstract¶
The secure and efficient processing of private information in the cloud computing paradigm is still an open issue. New security threats arise with the increasing volume of data into cloud storage, where cloud providers require high levels of trust, and data breaches are significant problems. Encrypting the data with conventional schemes is considered the best option to avoid security problems. However, a decryption process is necessary when the data must be processed, but it falls into the initial problem of data vulnerability. The user cannot operate on the data directly and must download it to perform the computations locally. In this context, Fully Homomorphic Encryption (FHE) is considered the holy grail of cryptography in order to solve cybersecurity problems, it allows a non-trustworthy third-party resource to blindly process encrypted information without disclosing confidential data. FHE is a valuable capability in a world of distributed computation and heterogeneous networking. In this survey, we present a comprehensive review of theoretical concepts, state-of-the-art, limitations, potential applications, and development tools in the domain of FHE. Moreover, we show the intersection of FHE and machine learning from a theoretical and a practical point of view and identify potential research directions to enrich Machine Learning as a Service, a new paradigm of cloud computing. Specifically, this paper aims to be a guide to researchers and practitioners interested in learning, applying, and extending knowledge in FHE over machine learning.
Source: pdf
Extracted details¶
| Field | Value | Source | Confidence |
|---|---|---|---|
| contribution | review of FHE theoretical concepts, state of the art and limitations | llm | 0.75 |
| contribution | overview of FHE development tools and libraries | llm | 0.75 |
| contribution | analysis of the intersection of FHE and machine learning | llm | 0.75 |
| contribution | identification of research directions for Machine Learning as a Service | llm | 0.75 |
| schemes | FHE | llm | 0.75 |
| libraries | SEAL | llm | 0.75 |
| libraries | PALISADE | llm | 0.75 |
| tasks | privacy-preserving machine learning | llm | 0.75 |
| tasks | Machine Learning as a Service | llm | 0.75 |
| tasks | cloud computing security | llm | 0.75 |
| threat model | non-trustworthy third-party cloud provider | llm | 0.75 |
| interaction | non-interactive FHE | llm | 0.75 |
| limitations | authors note further study is required beyond this guide | llm | 0.75 |
| llm relevance | low | llm | 0.75 |
Keyword mentions¶
Counts of vocabulary terms in the full text (first page of occurrence in brackets).
- scheme: Leveled / somewhat HE 8 [p.3], Partially homomorphic encryption 4 [p.3], NTRU 3 [p.4], RSA 3 [p.3], CKKS 2 [p.12]
- library: PALISADE 2 [p.11], Microsoft SEAL 2 [p.11], HElib 2 [p.11], cuHE 2 [p.12]
- model: Logistic regression 4 [p.8], AlexNet 2 [p.9], Decision tree 2 [p.8], CNN 1 [p.14]
- hardware: GPU 4 [p.9], CUDA 1 [p.12]
- technique: Bootstrapping 24 [p.3], Key switching 8 [p.3], Compiler 2 [p.12]
- assumption: LWE 5 [p.4], Lattice-based 5 [p.4]
- task: Medical / healthcare 4 [p.7], Genomics 2 [p.11]
- topic: Homomorphic encryption 110 [p.1], Privacy-preserving machine learning 7 [p.3], Open source 2 [p.11]
Files¶
| Path (under papers/) | Collection | Pages | Size | SHA-256 | Note |
|---|---|---|---|---|---|
references/ppml/surveys/pulido-gaytan-2020_survey-on-privacy-preserving-ml-with-fhe.pdf |
ppml/surveys | 15 | 422.5 KB | 13676d192e5d |
was Pulido-Gaytan et al. - 2020 - A Survey on Privacy-Preserving Machine Learning with Fully Homomorphic Encryption.pdf |
Database key: a-survey-on-privacy-preserving-machine-learning-with-fully-homomorphic · created 2026-11-05 · updated 2026-11-05 · edit with python3 tools/paperdb.py set a-survey-on-privacy-preserving-machine-learning-with-fully-homomorphic COLUMN VALUE