MétaCan
Menu
Back to cohort
Record W3197018685

Where Did You Learn That From? Surprising Effectiveness of Membership Inference Attacks Against Temporally Correlated Data in Deep Reinforcement Learning.

2021· preprint· en· W3197018685 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

VenuearXiv (Cornell University) · 2021
Typepreprint
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsUniversity of WaterlooMcGill University
Fundersnot available
KeywordsReinforcement learningAdversarial systemArtificial intelligenceReinforcementComputer scienceDeep learningInferenceMachine learningVulnerability (computing)Computer securityPsychologySocial psychology
DOInot available

Abstract

fetched live from OpenAlex

While significant research advances have been made in the field of deep reinforcement learning, a major challenge to widespread industrial adoption of deep reinforcement learning that has recently surfaced but little explored is the potential vulnerability to privacy breaches. In particular, there have been no concrete adversarial attack strategies in literature tailored for studying the vulnerability of deep reinforcement learning algorithms to membership inference attacks. To address this gap, we propose an adversarial attack framework tailored for testing the vulnerability of deep reinforcement learning algorithms to membership inference attacks. More specifically, we design a series of experiments to investigate the impact of temporal correlation, which naturally exists in reinforcement learning training data, on the probability of information leakage. Furthermore, we study the differences in the performance of \emph{collective} and \emph{individual} membership attacks against deep reinforcement learning algorithms. Experimental results show that the proposed adversarial attack framework is surprisingly effective at inferring the data used during deep reinforcement training with an accuracy exceeding $84\%$ in individual and $97\%$ in collective mode on two different control tasks in OpenAI Gym, which raises serious privacy concerns in the deployment of models resulting from deep reinforcement learning. Moreover, we show that the learning state of a reinforcement learning algorithm significantly influences the level of the privacy breach.

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)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Open science, Research integrity
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.570
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0050.012
Research integrity0.0010.003
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 head0.082
GPT teacher head0.240
Teacher spread0.158 · 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