MétaCan
Menu
Back to cohort
Record W4387451832 · doi:10.21203/rs.3.rs-3393386/v1

Critical Analysis of Privacy Risks in Machine Learning and Implications for Use of Health Data: A systematic review and meta-analysis on membership inference attacks

2023· review· en· W4387451832 on OpenAlexaff
Emily Walker, Jingyu Bu, Mohammadreza Pakseresht, Maeve E. Wickham, Lorraine Shack, Paula J. Robson, Nidhi Hegde

Bibliographic record

VenueResearch Square · 2023
Typereview
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsUniversity of AlbertaAlberta Health Services
Fundersnot available
KeywordsGeneralizationMeta-analysisMachine learningRandom forestArtificial intelligenceComputer scienceInferenceData miningStatisticsMathematicsMedicine

Abstract

fetched live from OpenAlex

Abstract Purpose. Machine learning(ML) has revolutionized data processing and analysis, with applications in health showing great promise. However, ML poses privacy risks, as models may reveal information about their training data. Developing frameworks to assess/mitigate privacy risks is essential, particularly for health data custodians responsible for adhering to ethical and legal standards in data use. In September 2022, we conducted a systematic review/meta-analysis to estimate the relative effects of factors hypothesized to contribute to ML privacy risk, focusing on membership inference attacks (MIA). Methods. Papers were screened for relevance to MIA, and selected for the meta-analysis if they contained attack performance(AP) metrics for attacks on models trained on numeric data. Random effects regression was used to estimate the adjusted average change in AP by model type, generalization gap and the density of training data in each region of input space (partitioned density). Residual sum of squares was used to determine the importance of variables on AP. Results. The systematic review and meta-analysis included 115 and 42 papers, respectively, comprising 1,910 experiments. The average AP ranged from 61.0% (95%CI:60.0%-63.0%; AUC)-74.0% (95%CI:72.0%-76.0%; recall). Higher partitioned density was inversely associated with AP for all model architectures, with the largest effect on decision trees. Higher generalization gap was linked to increased AP, predominantly affecting neural networks. Partitioned density was a better predictor of AP than generalization gap for most architectures. Conclusions. This is the first quantitative synthesis of MIA experiments, that highlights the effect of dataset composition on AP, particularly on decision trees, which are commonly used in health.

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.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.103
metaresearch head score (Gemma)0.296
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: Methods · Consensus signal: none
Study designCandidate signal: Meta-analysis · Consensus signal: none
GenreCandidate signal: Review · Consensus signal: Review
Teacher disagreement score0.897
Threshold uncertainty score0.546

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.1030.296
Meta-epidemiology (narrow)0.0030.002
Meta-epidemiology (broad)0.0110.031
Bibliometrics0.0080.007
Science and technology studies0.0010.003
Scholarly communication0.0050.005
Open science0.0030.003
Research integrity0.0030.004
Insufficient payload (model declined to judge)0.0040.000

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 head0.750
GPT teacher head0.609
Teacher spread0.141 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

Study designMeta-analysis
DomainMethods
GenreReview

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueResearch SquareSame topicPrivacy-Preserving Technologies in DataFrench-language works237,207