Elie Al ChichaDoctorant en Informatique
- LIUPPA
LIUPPA
IUT de Bayonne et du Pays BasqueCampus Montaury 2, Allées Montaury 64600 Anglet France
elie.al-chicha @ univ-pau.fr
Parcours
Expériences Professionnelles
|
July 2015 - Present |
Software Engineer, PORTALYS.net Develop windows application language c# , web service (java) , android mobile application, PHP and HTML website
|
|
August 2015 - |
Final Year Project, Antonine University SPLUNK (Search Processing Language) Technology and data mining
|
|
Mars 2016 - |
Research Internship Security and Privacy (Differential Privacy), Classification, Principal Component Analysis
|
|
July 2016 - |
Freelance for Antonine University Four Drupal websites for research units in Antonine University
|
|
Mars 2017 - |
Research Project for TICKET Lab - Antonine University. Differentially Private Image Classification The work was presented in “ICAR’17 conference”
|
|
Aug. 2017 - Present |
Research Project for TICKET Lab - Antonine University. Differentially Private Multi-Released Graphs |
Formations
|
2008 - 2011 |
Bachelor’s Degree in computer science, Lebanese University - faculty of science 2
|
|
2012 - 2016 |
Master’s Degree IN COMPUTER ENGINEERING, MULTIMEDIA, SYSTEMS, TELECOMMUNICATIONS AND NETWORKS, Antonine University
|
|
2018 - Present |
PhD in Computer Science, UPPA |
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
|
Directeur | |
|
Co-Directeur |
Publications
En cours.
