Search Results for author: Aidmar Wainakh

Found 2 papers, 1 papers with code

User-Level Label Leakage from Gradients in Federated Learning

2 code implementations19 May 2021 Aidmar Wainakh, Fabrizio Ventola, Till Müßig, Jens Keim, Carlos Garcia Cordero, Ephraim Zimmer, Tim Grube, Kristian Kersting, Max Mühlhäuser

Specifically, we investigate Label Leakage from Gradients (LLG), a novel attack to extract the labels of the users' training data from their shared gradients.

Federated Learning

Enhancing Privacy via Hierarchical Federated Learning

no code implementations23 Apr 2020 Aidmar Wainakh, Alejandro Sanchez Guinea, Tim Grube, Max Mühlhäuser

Federated learning suffers from several privacy-related issues that expose the participants to various threats.

Cryptography and Security

Cannot find the paper you are looking for? You can Submit a new open access paper.