Change search
ReferencesLink to record
Permanent link

Direct link
On reconstructability of quadratic utility functions from the iterations in gradient methods
KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre. KTH, School of Electrical Engineering (EES), Automatic Control.
2016 (English)In: Automatica, ISSN 0005-1098, E-ISSN 1873-2836, Vol. 66, 254-261 p.Article in journal (Refereed) PublishedText
Abstract [en]

In this paper, we consider a scenario where an eavesdropper can read the content of messages transmitted over a network. The nodes in the network are running a gradient algorithm to optimize a quadratic utility function where such a utility optimization is a part of a decision making process by an administrator. We are interested in understanding the conditions under which the eavesdropper can reconstruct the utility function or a scaled version of it and, as a result, gain insight into the decision-making process. We establish that if the parameter of the gradient algorithm, i.e., the step size, is chosen appropriately, the task of reconstruction becomes practically impossible for a class of Bayesian filters with uniform priors. We establish what step-size rules should be employed to ensure this. 

Place, publisher, year, edition, pages
Elsevier, 2016. Vol. 66, 254-261 p.
Keyword [en]
Statistical inference, Data privacy, Gradient methods, Data confidentiality, Parameter identification, Quadratic programming
National Category
Communication Systems
URN: urn:nbn:se:kth:diva-184949DOI: 10.1016/j.automatica.2016.01.014ISI: 000371099300029ScopusID: 2-s2.0-84959521193OAI: diva2:917819

QC 20160407

Available from: 2016-04-07 Created: 2016-04-07 Last updated: 2016-04-07Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Johansson, Mikael
By organisation
ACCESS Linnaeus CentreAutomatic Control
In the same journal
Communication Systems

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 25 hits
ReferencesLink to record
Permanent link

Direct link