Search Results for author:
Found 5 papers, 0 papers with code
Beyond Noise: Privacy-Preserving Decentralized Learning with Virtual Nodes
We theoretically prove the convergence of Shatter and provide a formal analysis demonstrating how Shatter reduces the efficacy of attacks compared to when exchanging full models between participating nodes.
Low-Cost Privacy-Aware Decentralized Learning
This paper introduces ZIP-DL, a novel privacy-aware decentralized learning (DL) algorithm that relies on adding correlated noise to each model update during the model training process.
Advancing Personalized Federated Learning: Group Privacy, Fairness, and Beyond
FL was proposed as a stepping-stone towards privacy-preserving machine learning, but it has been shown vulnerable to issues such as leakage of private information, lack of personalization of the model, and the possibility of having a trained model that is fairer to some groups than to others.
Group privacy for personalized federated learning
To cope with the issue of protecting the privacy of the clients and allowing for personalized model training to enhance the fairness and utility of the system, we propose a method to provide group privacy guarantees exploiting some key properties of $d$-privacy which enables personalized models under the framework of FL.
Multiwavelength analysis of low surface brightness galaxies to study possible dark matter signature
They are very rich in neutral hydrogen (HI) gas, which extends well beyond the stellar disks.
High Energy Astrophysical Phenomena Astrophysics of Galaxies
