Lossy Communication Subject to Statistical Parameter Privacy

Abstract : We investigate the problem of sharing (communi-cating) the outcomes of a memoryless source when some of its statistical parameters must be kept private. Privacy is measured in terms of the Bayesian statistical risk according to a desired loss function while the quality of the reconstruction is measured by the average per-letter distortion. We first bound -uniformly over all possible estimators- the expected risk from below. This information-theoretic bound depends on the mutual information between the parameters and the disclosed (noisy) samples. We then present an achievable scheme that guarantees an upper bound on the average distortion while keeping the risk above a desired threshold, even when the length of the sample increases.
Type de document :
Communication dans un congrès
2018 IEEE International Symposium on Information Theory (ISIT), Jun 2018, Vail, United States. 〈10.1109/isit.2018.8437690 〉
Liste complète des métadonnées

https://hal-centralesupelec.archives-ouvertes.fr/hal-01756020
Contributeur : Pablo Piantanida <>
Soumis le : samedi 31 mars 2018 - 11:12:55
Dernière modification le : mardi 28 août 2018 - 17:01:40

Identifiants

Citation

German Bassi, Pablo Piantanida, Mikael Skoglund. Lossy Communication Subject to Statistical Parameter Privacy. 2018 IEEE International Symposium on Information Theory (ISIT), Jun 2018, Vail, United States. 〈10.1109/isit.2018.8437690 〉. 〈hal-01756020〉

Partager

Métriques

Consultations de la notice

166