MétaCan
Menu
Back to cohort
Record W4391725330 · doi:10.14722/ndss.2024.23014

Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction

2024· article· en· W4391725330 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.
fundA Canadian funder is recorded on the work.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldDecision Sciences
TopicData Quality and Management
Canadian institutionsUniversity of British Columbia
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsOverconfidence effectInferenceComputer securityComputer scienceArtificial intelligencePsychologySocial psychology

Abstract

fetched live from OpenAlex

Machine learning (ML) models are vulnerable to membership inference attacks (MIAs), which determine whether a given input is used for training the target model.While there have been many efforts to mitigate MIAs, they often suffer from limited privacy protection, large accuracy drop, and/or requiring additional data that may be difficult to acquire.This work proposes a defense technique, HAMP that can achieve both strong membership privacy and high accuracy, without requiring extra data.To mitigate MIAs in different forms, we observe that they can be unified as they all exploit the ML model's overconfidence in predicting training samples through different proxies.This motivates our design to enforce less confident prediction by the model, hence forcing the model to behave similarly on the training and testing samples.HAMP consists of a novel training framework with high-entropy soft labels and an entropy-based regularizer to constrain the model's prediction while still achieving high accuracy.To further reduce privacy risk, HAMP uniformly modifies all the prediction outputs to become low-confidence outputs while preserving the accuracy, which effectively obscures the differences between the prediction on members and non-members.We conduct extensive evaluation on five benchmark datasets, and show that HAMP provides consistently high accuracy and strong membership privacy.Our comparison with seven state-ofthe-art defenses shows that HAMP achieves a superior privacyutility trade off than those techniques 1 . High accuracy AND Strong privacy High accuracy AND Strong privacy

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)0.005
metaresearch head score (Gemma)0.002
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesScholarly communication, Insufficient payload (model declined to judge)
Consensus categoriesInsufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: Not applicable
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.869
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0050.002
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0030.002
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0030.001

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 head0.218
GPT teacher head0.437
Teacher spread0.219 · 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

Quick stats

Citations21
Published2024
Admission routes2
Has abstractyes

Explore more

Same topicData Quality and ManagementFrench-language works237,207