MétaCan
Menu
Back to cohort
Record W7116896472 · doi:10.26599/tst.2024.9010243

From Model Parameters to Data Quality: Implicit Factor Evaluation of Model Extraction Attacks

2025· article· en· W7116896472 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

VenueTsinghua Science & Technology · 2025
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsArtificial Intelligence in Medicine (Canada)
FundersNatural Science Foundation of Guangdong ProvinceNational Natural Science Foundation of China
KeywordsSelection (genetic algorithm)Quality (philosophy)Range (aeronautics)Key (lock)AnnotationFocus (optics)Deep learningData quality

Abstract

fetched live from OpenAlex

Abstract Model extraction attacks (MEAs) pose a significant threat to deep learning (DL) models, where adversaries aim to steal the decision behavior of targeted DL models. While several works have shown the ability of a surrogate model to mimic the target DL model, the underlying factors that make a DL model vulnerable to MEAs are unclear. Analyzing these underlying factors is the key to enhancing the security of DL systems. This involves exploring MEAs in diverse scenarios to understand the relationship between their success and the features of DL systems. In this paper, we evaluate the underlying factors influencing MEAs from two crucial perspectives: the model’s intrinsic parameters and the quality of the data used. For the model’s intrinsic parameters, we focus on how the batch size, learning rate, and optimizer influence the effectiveness of MEAs. Regarding data quality, we conduct an in-depth analysis of how data annotation and selection affect MEAs’ success. Our study includes analyzing variations in batch size, five learning rates, eight optimizers, the impact of varying proportions of dirty data, and the effects of subtle changes in data richness. The results of our research reveal a diverse range of susceptibilities to MEAs.

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)0.003
metaresearch head score (Gemma)0.003
Version: codex-gemma-dda1882f352aValidation 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: none
Teacher disagreement score0.341
Threshold uncertainty score0.986

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.003
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.004
Science and technology studies0.0000.001
Scholarly communication0.0000.002
Open science0.0050.003
Research integrity0.0000.000
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 head0.155
GPT teacher head0.461
Teacher spread0.306 · 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