We examine the interplay between learning and privacy over multiagent consensus networks. The learning objective of each individual agent consists of computing some global network statistic, and is accomplished by means of a consensus protocol. The privacy objective consists of preventing inference of the individual agents' data from the information exchanged during the consensus stages, and is accomplished by adding some artificial noise to the observations (obfuscation). An analytical characterization of the learning and privacy performance is provided, with reference to a consensus perturbing and to a consensus-preserving obfuscation strategy.

Learning With Privacy in Consensus + Obfuscation / Braca, P; Lazzeretti, Riccardo; Marano, S; Matta, S.. - In: IEEE SIGNAL PROCESSING LETTERS. - ISSN 1070-9908. - 23:9(2016), pp. 1174-1178. [10.1109/LSP.2016.2587327]

Learning With Privacy in Consensus + Obfuscation

LAZZERETTI, RICCARDO
;
2016

Abstract

We examine the interplay between learning and privacy over multiagent consensus networks. The learning objective of each individual agent consists of computing some global network statistic, and is accomplished by means of a consensus protocol. The privacy objective consists of preventing inference of the individual agents' data from the information exchanged during the consensus stages, and is accomplished by adding some artificial noise to the observations (obfuscation). An analytical characterization of the learning and privacy performance is provided, with reference to a consensus perturbing and to a consensus-preserving obfuscation strategy.
2016
Consensus; Multi-agent systems; obfuscation, privacy;
01 Pubblicazione su rivista::01a Articolo in rivista
Learning With Privacy in Consensus + Obfuscation / Braca, P; Lazzeretti, Riccardo; Marano, S; Matta, S.. - In: IEEE SIGNAL PROCESSING LETTERS. - ISSN 1070-9908. - 23:9(2016), pp. 1174-1178. [10.1109/LSP.2016.2587327]
File allegati a questo prodotto
File Dimensione Formato  
Braca_Learning-With-Privacy_2016.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 421.93 kB
Formato Adobe PDF
421.93 kB Adobe PDF   Contatta l'autore
Braca_preprint_Learning-With-Privacy_2016.pdf

accesso aperto

Note: https://ieeexplore.ieee.org/document/7506018
Tipologia: Documento in Pre-print (manoscritto inviato all'editore, precedente alla peer review)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 11.73 MB
Formato Adobe PDF
11.73 MB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/967176
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 18
  • ???jsp.display-item.citation.isi??? 19
social impact