Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures

@inproceedings{Fredrikson2015ModelIA,
  title={Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures},
  author={Matt Fredrikson and Somesh Jha and Thomas Ristenpart},
  booktitle={ACM Conference on Computer and Communications Security},
  year={2015}
}
Machine-learning (ML) algorithms are increasingly utilized in privacy-sensitive applications such as predicting lifestyle choices, making medical diagnoses, and facial recognition. In a model inversion attack, recently introduced in a case study of linear classifiers in personalized medicine by Fredrikson et al., adversarial access to an ML model is abused to learn sensitive genomic information about individuals. Whether model inversion attacks apply to settings outside theirs, however, is… CONTINUE READING

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 228 CITATIONS

Image Disguising for Privacy-preserving Deep Learning

VIEW 7 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Adversarial Neural Network Inversion via Auxiliary Knowledge Alignment

VIEW 20 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Latent-Space-Level Image Anonymization With Adversarial Protector Networks

  • IEEE Access
  • 2019
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Generating Artificial Data for Private Deep Learning

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Learning from Differentially Private Neural Activations with Edge Computing

  • 2018 IEEE/ACM Symposium on Edge Computing (SEC)
  • 2018
VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Privacy-preserving Machine Learning through Data Obfuscation

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Reaching Data Confidentiality and Model Accountability on the CalTrain

  • ArXiv
  • 2018
VIEW 7 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2015
2019

CITATION STATISTICS

  • 30 Highly Influenced Citations

  • Averaged 70 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-4 OF 4 REFERENCES