Regression Model Fitting under Differential Privacy and Model Inversion Attack

@inproceedings{Wang2015RegressionMF,
  title={Regression Model Fitting under Differential Privacy and Model Inversion Attack},
  author={Yue Wang and Cheng Si and Xintao Wu},
  booktitle={IJCAI},
  year={2015}
}
Differential privacy preserving regression models guarantee protection against attempts to infer whether a subject was included in the training set used to derive a model. It is not designed to protect attribute privacy of a target individual when model inversion attacks are launched. In model inversion attacks, an adversary uses the released model to make predictions of sensitive attributes (used as input to the model) of a target individual when some background information about the target… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 32 references

Theory of Cryptography

Lecture Notes in Computer Science • 2004
View 14 Excerpts
Highly Influenced

In PAKDD (2)

Yue Wang, Xintao Wu, Leting Wu. Differential privacy preserving spectral graph analysis
pages 329–340, • 2013

Transactions on Data Privacy

Yue Wang, Xintao Wu. Preserving differential privacy in degree-corr generation
6:127–145, • 2013
View 1 Excerpt

Similar Papers

Loading similar papers…