IEEE

Asynchronous Federated Learning with non-convex client objective functions and heterogeneous dataset

Abstract: Federated Learning is a distributed machine learning paradigm that enables model training across decentralized devices holding local data, thereby preserving data privacy and reducing the ...
IEEE

A Novel Approach for Differential Privacy-Preserving Federated Learning

Abstract: In this paper, we start with a comprehensive evaluation of the effect of adding differential privacy (DP) to federated learning (FL) approaches, focusing on methodologies employing global ...

OpenAI’s New AI Foundations Course Promises ‘Job-Ready’ Skills and Credential

AI firm debuts its first certification program with ChatGPT-based courses for workers and K-12 teachers, starting with AI ...
GitHub

Statistical Test-based Adversarial Client Detection in Federated Learning under Poisoning Attacks

This repository contains the technical implementation of the paper Statistical Test-based Adversarial Client Detection in Federated Learning under Poisoning Attacks, as well as proof of its results.