Master Thesis: Differentially Private Federated Learning in Online Social Networks

Forumsregeln
Auch ohne Registrierung können Beiträge in diesem Unterforum geschrieben werden.

Antwort erstellen

Bitte gib deine E-Mail-Adresse an, demit du nachträglich Updates zu deinem Post hinzufügen kannst.


Diese Frage dient dazu, das automatisierte Versenden von Formularen durch Spam-Bots zu verhindern.
Smilies
:D :) :( :o :shock: :? 8) :lol: :x :P :oops: :cry: :evil: :twisted: :roll: :wink: :!: :?: :idea: :arrow: :| :mrgreen:

BBCode ist eingeschaltet
[img] ist eingeschaltet
[flash] ist ausgeschaltet
[url] ist eingeschaltet
Smilies sind eingeschaltet

Die letzten Beiträge des Themas
   

Ansicht erweitern Die letzten Beiträge des Themas: Master Thesis: Differentially Private Federated Learning in Online Social Networks

Master Thesis: Differentially Private Federated Learning in Online Social Networks

von Aidmar » 12. Jul 2019 12:07

Master Thesis
Title: Differentially Private Federated Learning in Online Social Networks
Telecooperation Lab, Computer Science department, TU-Darmstadt

Google uses the federated learning technique to build machine learning models based on distributed data. Users train the model locally on their data and send only the model updates to the server, which aggregates all updates to optimize the global model. The federated learning technique is prone to several attacks aiming at revealing information about individual users.

In this thesis, we will work on protecting user data using Differential Privacy (DP) with federated learning. DP distorts the data by adding noise to it. However, adding noise to the data reduces its utility. Exploiting the trust among users in online social networks, we aim to balance the trade-off between privacy and data utility.

Required skills:
-Interested in privacy and security
-Interested in graph theory
-Programming skills (preferably Python)

Contact: Aidmar Wainakh (wainakh@tk.tu-darmstadt.de)

Please make your email's subject: [DPFL THESIS APPLICANT]

Nach oben