.png){kind=icon}
Return
Correlation inference attacks against machine learning models
.png){kind=icon}
OA
AI
DOI：10.1126/sciadv.adj9260.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Despite machine learning models being widely used today, the relationship between a model and its training dataset is not well understood. We explore correlation inference attacks, whether and when a model leaks information about the correlations between the input variables of its training dataset. We first propose a model-less attack, where an adversary exploits the spherical parameterization of correlation matrices alone to make an informed guess. Second, we propose a model-based attack, where an adversary exploits black-box model access to infer the correlations using minimal and realistic assumptions. Third, we evaluate our attacks against logistic regression and multilayer perceptron models on three tabular datasets and show the models to leak correlations. We lastly show how extracted correlations can be used as building blocks for attribute inference attacks and enable weaker adversaries. Our results raise fundamental questions on what a model does and should remember from its training set.
Journal
IF:
12.5
Papers:
2.1W
Citations:
21.1W
Organization
Cited Papers
ShareSaveMass-spectrometric characterization of cisplatin binding sites on native and denatured ubiquitin
PREAI
ShareSaveAlgorithms that remember: model inversion attacks and data protection law.png)
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES
OAAI
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCESIF3.7
OAAIShareSaveShareSave
View more