MétaCan
Menu
Back to cohort
Record W2801491268 · doi:10.1515/popets-2018-0024

Privacy-preserving Machine Learning as a Service

2018· article· en· W2801491268 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueProceedings on Privacy Enhancing Technologies · 2018
Typearticle
Languageen
FieldComputer Science
TopicCryptography and Data Security
Canadian institutionsUniversity of Saskatchewan
FundersCenter for Discrete Mathematics and Theoretical Computer ScienceNational Science Foundation
KeywordsComputer scienceHomomorphic encryptionEncryptionCloud computingMachine learningArtificial intelligenceArtificial neural networkDeep learningDomain (mathematical analysis)Information privacyService providerRaw dataService (business)Data miningComputer security

Abstract

fetched live from OpenAlex

Abstract Machine learning algorithms based on deep Neural Networks (NN) have achieved remarkable results and are being extensively used in different domains. On the other hand, with increasing growth of cloud services, several Machine Learning as a Service (MLaaS) are offered where training and deploying machine learning models are performed on cloud providers’ infrastructure. However, machine learning algorithms require access to the raw data which is often privacy sensitive and can create potential security and privacy risks. To address this issue, we present CryptoDL, a framework that develops new techniques to provide solutions for applying deep neural network algorithms to encrypted data. In this paper, we provide the theoretical foundation for implementing deep neural network algorithms in encrypted domain and develop techniques to adopt neural networks within practical limitations of current homomorphic encryption schemes. We show that it is feasible and practical to train neural networks using encrypted data and to make encrypted predictions, and also return the predictions in an encrypted form. We demonstrate applicability of the proposed CryptoDL using a large number of datasets and evaluate its performance. The empirical results show that it provides accurate privacy-preserving training and classification.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.004
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Open science
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.489
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.004
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.002
Science and technology studies0.0010.000
Scholarly communication0.0010.002
Open science0.0060.006
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.017
GPT teacher head0.256
Teacher spread0.239 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it