• Aide
  • Recherche
  • Facebook
  • Twitter
LIUPPA
Vous êtes ici :

    Elie Al ChichaDoctorant en Informatique

    • LIUPPA
    • Parcours
    • Thèmes de recherche
    • Projets
    • Publications

    Parcours

    Expériences Professionnelles

     

    Formations

    Thèmes de recherche

    • Differential Privacy
    • Local Differential Privacy
    • Blowfish Privacy
    • Image Classification
    • Social Networks, Graphs, CDRs

    Projets

    Thèse

    Titre

    Differentially Private Image Classification

    Description

    In this project, our aim is to design and develop an anonymous full-duplex image classification service under Differential Privacy. We work under the assumption that both, the cloud and the querier are semi-trusted entities, thus their data should remain safe and confidential. That is, neither the querier nor the cloud should be able to link an individual to an image on the cloud while maintaining, to a certain extent, suitable classification accuracy. We use Principal Component Analysis (PCA) to transform sample images into anonymized vectors; differentially private synopsis of PCA vectors, and we ensure that these vectors remain unidentifiable.

     

    Membres

    Publications

    En cours.