Bayesian probability models uncertain knowledge and learning from observations. As a defining feature of optimal adversarial behaviour, Bayesian reasoning forms the basis of safety properties in contexts such as privacy and fairness. Probabilistic programming is a convenient implementation of Bayesian reasoning but the adversarial setting imposes obstacles to its use: approximate inference can underestimate adversary knowledge and exact inference is impractical in cases covering large state spaces.

By abstracting distributions, the semantics of a probabilistic language, and inference, jointly termed probabilistic abstract interpretation, we demonstrate adversary models both approximate and sound.

We apply the techniques to build a privacy protecting monitor and describe how to trade off the precision and computational cost in its implementation all the while remaining sound with respect to privacy risk bounds.

[ http ]

@incollection{trilla20probprog,
  title = {Probabilistic Abstract Interpretation: Sound Inference and Application to Privacy},
  booktitle = {Foundations of Probabilistic Programming},
  author = {Jose Manuel Calder\'{o}n Trilla and Michael Hicks and Stephen Magill and Piotr Mardziel and Ian Sweet},
  editor = {Gilles Barthe and Joost-Pieter Katoen and Alexandra Silva},
  chapter = 11,
  pages = {361--389},
  month = nov,
  year = 2020,
  publisher = {Cambridge University Press}
}

This file was generated by bibtex2html 1.99.