MétaCan
Menu
Back to cohort
Record W4311530262 · doi:10.3390/electronics11234007

Privacy-Enhanced Federated Learning: A Restrictively Self-Sampled and Data-Perturbed Local Differential Privacy Method

2022· article· en· W4311530262 on OpenAlex
Jianzhe Zhao, Mengbo Yang, Ronglin Zhang, Wuganjing Song, Jingran Feng, Stan Matwin

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

VenueElectronics · 2022
Typearticle
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsDalhousie University
FundersNational Natural Science Foundation of China
KeywordsDifferential privacyComputer scienceMNIST databaseRandomnessInformation privacyVariance (accounting)Federated learningData miningSampling (signal processing)Machine learningArtificial intelligenceDeep learningComputer securityDetector

Abstract

fetched live from OpenAlex

As a popular distributed learning framework, federated learning (FL) enables clients to conduct cooperative training without sharing data, thus having higher security and enjoying benefits in processing large-scale, high-dimensional data. However, by sharing parameters in the federated learning process, the attacker can still obtain private information from the sensitive data of participants by reverse parsing. Local differential privacy (LDP) has recently worked well in preserving privacy for federated learning. However, it faces the inherent problem of balancing privacy, model performance, and algorithm efficiency. In this paper, we propose a novel privacy-enhanced federated learning framework (Optimal LDP-FL) which achieves local differential privacy protection by the client self-sampling and data perturbation mechanisms. We theoretically analyze the relationship between the model accuracy and client self-sampling probability. Restrictive client self-sampling technology is proposed which eliminates the randomness of the self-sampling probability settings in existing studies and improves the utilization of the federated system. A novel, efficiency-optimized LDP data perturbation mechanism (Adaptive-Harmony) is also proposed, which allows an adaptive parameter range to reduce variance and improve model accuracy. Comprehensive experiments on the MNIST and Fashion MNIST datasets show that the proposed method can significantly reduce computational and communication costs with the same level of privacy and model utility.

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)0.010
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Meta-epidemiology (narrow), Open science
Consensus categoriesOpen science
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.822
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.010
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0300.172
Research integrity0.0000.002
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 head0.029
GPT teacher head0.300
Teacher spread0.271 · 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