MétaCan
Menu
Back to cohort
Record W4386215192 · doi:10.1109/csf57540.2023.00013

Investigating Membership Inference Attacks under Data Dependencies

2023· article· en· W4386215192 on OpenAlexafffund
Thomas J. Humphries, Simon Oya, Lindsey Tulloch, Matthew Rafuse, Ian Goldberg, Urs Hengartner, Florian Kerschbaum

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsUniversity of Waterloo
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsInferenceSet (abstract data type)Computer sciencePoint (geometry)Training setIndependent and identically distributed random variablesData setArtificial intelligenceStatistical inferenceMachine learningData miningMathematicsRandom variableStatistics

Abstract

fetched live from OpenAlex

Training machine learning models on privacy-sensitive data has become a popular practice, driving innovation in ever-expanding fields. This has opened the door to new attacks that can have serious privacy implications. One such attack, the Membership Inference Attack (MIA), exposes whether or not a particular data point was used to train a model. A growing body of literature uses Differentially Private (DP) training algorithms as a defence against such attacks. However, these works evaluate the defence under the restrictive assumption that all members of the training set, as well as non-members, are independent and identically distributed. This assumption does not hold for many real-world use cases in the literature. Motivated by this, we evaluate membership inference with statistical dependencies among samples and explain why DP does not provide meaningful protection (the privacy parameter$\epsilon$scales with the training set size$n$) in this more general case. We conduct a series of empirical evaluations with off-the-shelf MIAs using training sets built from real-world data showing different types of dependencies among samples. Our results reveal that training set dependencies can severely increase the performance of MIAs, and therefore assuming that data samples are statistically independent can significantly underestimate the performance of MIAs.

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)0.020
metaresearch head score (Gemma)0.111
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.020
Threshold uncertainty score0.106

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0200.111
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0010.001
Science and technology studies0.0020.003
Scholarly communication0.0020.009
Open science0.0030.005
Research integrity0.0030.006
Insufficient payload (model declined to judge)0.0020.000

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 head0.246
GPT teacher head0.370
Teacher spread0.124 · 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.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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

Citations18
Published2023
Admission routes2
Has abstractyes

Explore more

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