2020 IEEE International Symposium
on Information Theory
21-26 June 2020 • Los Angeles, California, USA
| Paper ID | P.3.5 | ||
| Paper Title | Privacy Amplification of Iterative Algorithms via Contraction Coefficients | ||
| Authors | Shahab Asoodeh, Harvard University, United States; Mario Diaz, Universidad Nacional Autonoma de Mexico, Mexico; Flavio P. Calmon, Harvard University, United States | ||
| Session | P.3: Information Privacy I | ||
| Presentation | Lecture | ||
| Track | Cryptography, Security and Privacy | ||
| Manuscript | Click here to download the manuscript | ||
| Virtual Presentation | Click here to watch in the Virtual Symposium | ||
| Abstract | We investigate the framework of privacy amplification by iteration, recently proposed by Feldman et al., from an information-theoretic lens. We demonstrate that differential privacy guarantees of iterative mappings can be determined by a direct application of contraction coefficients derived from strong data processing inequalities for f-divergences. In particular, by generalizing the Dobrushin's contraction coefficient for total variation distance to an f-divergence known as E_\gamma-divergence, we derive tighter bounds on the differential privacy parameters of the projected noisy stochastic gradient descent algorithm with hidden intermediate updates. | ||
Plan Ahead
2021 IEEE International Symposium on Information Theory
11-16 July 2021 | Melbourne, Victoria, Australia
