11 citations · 22 across the 44 of their papers we have counts for
4 papers · 1 filter
Federated Learning with Heterogeneous Differential Privacy
Nasser Aldaghri, Hessam Mahdavifar, Ahmad Beirami
Federated learning (FL) takes a first step towards privacy-preserving machine learning by training models while keeping client data local. Models trained using FL may still leak pr…
ApproxIFER: A Model-Agnostic Approach to Resilient and Robust Prediction Serving Systems
Mahdi Soleymani, Ramy E. Ali, Hessam Mahdavifar +1
Due to the surge of cloud-assisted AI services, the problem of designing resilient prediction serving systems that can effectively cope with stragglers/failures and minimize respon…
Coded Machine Unlearning
Nasser Aldaghri, Hessam Mahdavifar, Ahmad Beirami
There are applications that may require removing the trace of a sample from the system, e.g., a user requests their data to be deleted, or corrupted data is discovered. Simply remo…
Privacy-Preserving Distributed Learning in the Analog Domain
Mahdi Soleymani, Hessam Mahdavifar, A. Salman Avestimehr
We consider the critical problem of distributed learning over data while keeping it private from the computational servers. The state-of-the-art approaches to this problem rely on…