Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 21, 2025

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.5K

Correlation inference attacks against machine learning models.

Ana-Maria Creţu1, Florent Guépin2, Yves-Alexandre de Montjoye2

  • 1EPFL, Lausanne, Switzerland.

Science Advances
|July 10, 2024
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Correlation and Regression00:53

Correlation and Regression

1.2K
In statistics, correlation describes the degree of association between two variables. In the subfield of linear regression, correlation is mathematically expressed by the correlation coefficient, which describes the strength and direction of the relationship between two variables. The coefficient is symbolically represented by 'r' and ranges from -1 to +1. A positive value indicates a positive correlation where the two variables move in the same direction. A negative value suggests a...
1.2K
Correlation01:09

Correlation

11.7K
In statistics, two variables are said to be correlated if the values of one variable are associated with the other variable. Depending on the relationship between two variables, correlation can be of three types– positive correlation, negative correlation, and zero correlation.
Two variables, for example, a and b, are said to be positively correlated if both variables move in the same direction. In other words, a positive correlation exists between two variables, a and b, if:
11.7K
Cause and Effect01:53

Cause and Effect

10.9K
While variables are sometimes correlated because one does cause the other, it could also be that some other factor, a confounding variable, is actually causing the systematic movement in our variables of interest. For instance, as sales in ice cream increase, so does the overall rate of crime. Is it possible that indulging in your favorite flavor of ice cream could send you on a crime spree? Or, after committing crime do you think you might decide to treat yourself to a cone?
10.9K
Correlations02:20

Correlations

32.8K
Correlation means that there is a relationship between two or more variables (such as ice cream consumption and crime), but this relationship does not necessarily imply cause and effect. When two variables are correlated, it simply means that as one variable changes, so does the other. We can measure correlation by calculating a statistic known as a correlation coefficient. A correlation coefficient is a number from -1 to +1 that indicates the strength and direction of the relationship between...
32.8K
Calculating and Interpreting the Linear Correlation Coefficient01:11

Calculating and Interpreting the Linear Correlation Coefficient

5.9K
The correlation coefficient, r, developed by Karl Pearson in the early 1900s, is numerical and provides a measure of strength and direction of the linear association between the independent variable, x, and the dependent variable, y. Hence, it is also known as the Pearson product-moment correlation coefficient. It can be calculated using the following equation:
5.9K
Correlation and Causation01:27

Correlation and Causation

37.6K
Statistical tests can calculate whether there is a relationship, or correlation, between independent and dependent variables. An indirect relationship of the variables signifies a correlation, while a direct relationship shows causation. If it is determined that no connection exists between the variables, then the correlation is a coincidence.
Correlation versus Causation
If the dependent variable increases or decreases when the independent variable increases, there is a positive or negative...
37.6K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

The mosaic memory of large language models.

Nature communications·2026
Same author

Anonymization: The imperfect science of using data while preserving privacy.

Science advances·2024
Same author

Expanding the attack surface: Robust profiling attacks threaten the privacy of sparse behavioral data.

Science advances·2022
Same author

Interaction data are identifiable even across long periods of time.

Nature communications·2022
Same author

On the difficulty of achieving Differential Privacy in practice: user-level guarantees in aggregate location data.

Nature communications·2022
Same author

Mapping poverty using mobile phone and satellite data.

Journal of the Royal Society, Interface·2017
Same journal

Taphonomic analysis at Liang Bua reveals the behavioral and technological capabilities of <i>Homo floresiensis</i>.

Science advances·2026
Same journal

Targeting granule initiation and amyloplast structure to create giant starch granules in wheat.

Science advances·2026
Same journal

A meta-analysis of carbon losses and gains from tropical moist forest degradation and regeneration.

Science advances·2026
Same journal

Ancient DNA reveals elite dynastic rule among Iron Age Eurasian Steppe nomads.

Science advances·2026
Same journal

Targeting astrocytic Dp71 attenuates BBB disruption after traumatic brain injury through WTAP-associated m<sup>6</sup>A regulation of MMP2.

Science advances·2026
Same journal

Pancreatic α cells are required for nutrient homeostasis by regulating dynamic β cell networks in islets.

Science advances·2026
See all related articles

Machine learning models can inadvertently reveal sensitive correlations from their training data. Researchers developed new attacks to demonstrate this information leakage, raising privacy concerns.

Area of Science:

  • Machine Learning
  • Data Privacy
  • Cybersecurity

Background:

  • Machine learning models are increasingly prevalent, yet their understanding of training data relationships remains limited.
  • The potential for models to leak sensitive information about their training datasets is a growing concern.

Purpose of the Study:

  • To investigate correlation inference attacks and determine if machine learning models leak information about correlations within their training data.
  • To develop and evaluate novel methods for inferring these correlations.

Main Methods:

  • Proposed a model-less attack leveraging the spherical parameterization of correlation matrices.
  • Developed a model-based attack using black-box model access with minimal assumptions.
  • Evaluated attacks on logistic regression and multilayer perceptron models using three tabular datasets.

More Related Videos

An R-Based Landscape Validation of a Competing Risk Model
05:37

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

2.0K
Author Spotlight: Emerging Technologies and Advanced Tools for Decoding Metabolomics Data Analysis
07:11

Author Spotlight: Emerging Technologies and Advanced Tools for Decoding Metabolomics Data Analysis

Published on: November 10, 2023

2.3K

Related Experiment Videos

Last Updated: Jun 21, 2025

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.5K
An R-Based Landscape Validation of a Competing Risk Model
05:37

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

2.0K
Author Spotlight: Emerging Technologies and Advanced Tools for Decoding Metabolomics Data Analysis
07:11

Author Spotlight: Emerging Technologies and Advanced Tools for Decoding Metabolomics Data Analysis

Published on: November 10, 2023

2.3K

Main Results:

  • Demonstrated that logistic regression and multilayer perceptron models leak correlations from their training data.
  • Showcased how extracted correlations can be utilized in attribute inference attacks.
  • Highlighted that these attacks can empower adversaries with weaker capabilities.

Conclusions:

  • Machine learning models retain and can leak information about the correlations present in their training datasets.
  • The findings necessitate a re-evaluation of what information models should retain from training data.
  • Raises fundamental questions about model memorization and data privacy in machine learning.