Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting

By Samuel Yeom, Irene Giacomelli, Matt Fredrikson, Somesh Jha. 2017

1,558 citations recorded by the source corpus.

Machine learning algorithms, when applied to sensitive data, pose a distinct threat to privacy. A growing body of prior work demonstrates that models produced by these algorithms may leak specific private information in the training data to an attacker, either through the models' structure or their observable behavior. However, the underlying cause of this privacy risk is not well understood beyond a handful of anecdotal accounts that suggest overfitting and influence might play a role. This paper examines the effect that overfitting and influence have on the ability of an attacker to learn information about the training data from machine learning models, either through training set membership inference or attribute inference attacks. Using both formal and empirical analyses, we illustrate a clear relationship between these factors and the privacy risk that arises in several popular machine learning algorithms. We find that overfitting is sufficient to allow an attacker to perform membership inference and, when the target attribute meets certain conditions about its influence, attribute inference attacks. Interestingly, our formal analysis also shows that overfitting is not necessary for these attacks and begins to shed light on what other factors may be in play. Finally, we explore the connection between membership inference and attribute inference, showing that there are deep connections between the two that lead to effective new attacks.

Subfields: Artificial Intelligence, Safety Research, Safety, Robustness & Interpretability, Privacy & Security

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Percy Liang
  2. Mohit Bansal
  3. Yoshua Bengio
  4. Quoc V. Le
  5. Luke S. Zettlemoyer
  6. Nicholas Carlini
  7. Jianfeng Gao
  8. Florian Tramèr

In Safety Research

  1. Prateek Mittal
  2. Liwei Song
  3. Reza Shokri
  4. Philip S. Yu
  5. Lichao Sun
  6. Gillian Dobbie
  7. Hongsheng Hu
  8. Zoran A. Salcic

In Safety, Robustness & Interpretability

  1. Nicholas Carlini
  2. Florian Tramèr
  3. Nicolas Papernot
  4. Reza Shokri
  5. Dawn Song
  6. Prateek Mittal
  7. Yang Zhang
  8. Liwei Song

In Privacy & Security

  1. Peter Kairouz
  2. Abhradeep Thakurta
  3. Vitaly Feldman
  4. Kunal Talwar
  5. Borja Balle
  6. Om Thakkar
  7. Rasmus Pagh
  8. H. Brendan McMahan

Citations in the corpus