Skip to Main content Skip to Navigation
Conference papers

Membership Inference Attacks on Aggregated Time Series with Linear Programming

Antonin Voyez 1, 2 Tristan Allard 3 Gildas Avoine 3 Pierre Cauchois 1 Elisa Fromont 2, 4 Matthieu Simonin 5 
2 LACODAM - Large Scale Collaborative Data Mining
Inria Rennes – Bretagne Atlantique , IRISA-D7 - GESTION DES DONNÉES ET DE LA CONNAISSANCE
3 SPICY - Security & PrIvaCY
IRISA-D1 - SYSTÈMES LARGE ÉCHELLE
5 MYRIADS - Design and Implementation of Autonomous Distributed Systems
Inria Rennes – Bretagne Atlantique , IRISA-D1 - SYSTÈMES LARGE ÉCHELLE
Abstract : Aggregating data is a widely used technique to protect privacy. Membership inference attacks on aggregated data aim to infer whether a specific target belongs to a given aggregate. We propose to study how aggregated time series data can be susceptible to simple membership inference privacy attacks in the presence of adversarial background knowledge. We design a linear programming attack that strongly benefits from the number of data points published in the series and show on multiple public datasets how vulnerable the published data can be if the size of the aggregated data is not carefully balanced with the published time series length. We perform an extensive experimental evaluation of the attack on multiple publicly available datasets. We show the vulnerability of aggregates made of thousands of time series when the aggregate length is not carefully balanced with the published length of the time series.
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03726234
Contributor : Voyez Antonin Connect in order to contact the contributor
Submitted on : Monday, July 18, 2022 - 12:12:51 PM
Last modification on : Friday, August 5, 2022 - 2:54:52 PM

File

article_ksa_secrypt.pdf
Files produced by the author(s)

Identifiers

Citation

Antonin Voyez, Tristan Allard, Gildas Avoine, Pierre Cauchois, Elisa Fromont, et al.. Membership Inference Attacks on Aggregated Time Series with Linear Programming. SECRYPT 2022 - 19th International Conference on Security and Cryptography, Jul 2022, Lisbon, France. pp.193-204, ⟨10.5220/0011276100003283⟩. ⟨hal-03726234⟩

Share

Metrics

Record views

33

Files downloads

17