Estimating g-Leakage via Machine Learning

@article{Romanelli2020EstimatingGV,
  title={Estimating g-Leakage via Machine Learning},
  author={Marco Romanelli and Konstantinos Chatzikokolakis and C. Palamidessi and P. Piantanida},
  journal={Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security},
  year={2020}
}
  • Marco Romanelli, Konstantinos Chatzikokolakis, +1 author P. Piantanida
  • Published 2020
  • Computer Science, Mathematics
  • Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security
  • This paper considers the problem of estimating the information leakage of a system in the black-box scenario, i.e. when the system's internals are unknown to the learner, or too complicated to analyze, and the only available information are pairs of input-output data samples, obtained by submitting queries to the system or provided by a third party. The frequentist approach relies on counting the frequencies to estimate the input-output conditional probabilities, however this method is not… CONTINUE READING

    References

    SHOWING 1-2 OF 2 REFERENCES
    Correlated Secrets in Quantitative Information Flow
    • 6
    • Highly Influential
    • PDF
    Protecting location privacy: optimal strategy against localization attacks
    • 308
    • Highly Influential
    • PDF