AI safety researcher

Claude Castelluccia

Google Scholar dblp Homepage

Latest AI safety papers

On this site: 5 papers

September 2021

Towards a Governance Framework for Brain Data
Sep 24arXiv ↗

February 2021

Constrained Differentially Private Federated Learning for Low-bandwidth Devices
Feb 27arXiv ↗

November 2020

Compression Boosts Differentially Private Federated Learning
Nov 10arXiv ↗

October 2020

Federated Learning in Adversarial Settings
Oct 15arXiv ↗

September 2017

Differentially Private Mixture of Generative Neural Networks
Sep 13arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.