Logo des Repositoriums

Auflistung nach Autor:in "Mohammadi, Esfandiar"

1 - 2 von 2
  • Zeitschriftenartikel
    Lifting in Support of Privacy-Preserving Probabilistic Inference
    (KI - Künstliche Intelligenz: Vol. 38, No. 3, 2024) Gehrke, Marcel; Liebenow, Johannes; Mohammadi, Esfandiar; Braun, Tanya
    Privacy-preserving inference aims to avoid revealing identifying information about individuals during inference. Lifted probabilistic inference works with groups of indistinguishable individuals, which has the potential to prevent tracing back a query result to a particular individual in a group. Therefore, we investigate how lifting, by providing anonymity, can help preserve privacy in probabilistic inference. Specifically, we show correspondences between k -anonymity and lifting and present s-symmetry as an analogue as well as PAULI, a privacy-preserving inference algorithm that ensures s-symmetry during query answering.
  • Zeitschriftenartikel
    PrivAgE: A Toolchain for Privacy-Preserving Distributed Aggregation on Edge-Devices
    (KI - Künstliche Intelligenz: Vol. 38, No. 3, 2024) Liebenow, Johannes; Imort, Timothy; Fuchs, Yannick; Heisel, Marcel; Käding, Nadja; Rupp, Jan; Mohammadi, Esfandiar
    Valuable insights, such as frequently visited environments in the wake of the COVID-19 pandemic, can oftentimes only be gained by analyzing sensitive data spread across edge-devices like smartphones. To facilitate such an analysis, we present a toolchain called PrivAgE for a distributed, privacy-preserving aggregation of local data by taking the limited resources of edge-devices into account. The distributed aggregation is based on secure summation and simultaneously satisfies the notion of differential privacy. In this way, other parties can neither learn the sensitive data of single clients nor a single client’s influence on the final result. We perform an evaluation of the power consumption, the running time and the bandwidth overhead on real as well as simulated devices and demonstrate the flexibility of our toolchain by presenting an extension of the summation of histograms to distributed clustering.