no code implementations • 16 Aug 2022 • Hamid Mozaffari, Virendra J. Marathe, Dave Dice
We present FedPerm, a new FL algorithm that addresses both these problems by combining a novel intra-model parameter shuffling technique that amplifies data privacy, with Private Information Retrieval (PIR) based techniques that permit cryptographic aggregation of clients' model updates.
no code implementations • 7 Jun 2022 • Anshuman Suri, Pallika Kanani, Virendra J. Marathe, Daniel W. Peterson
Using these attacks, we estimate subject membership inference risk on real-world data for single-party models as well as FL scenarios.
no code implementations • 7 Jun 2022 • Virendra J. Marathe, Pallika Kanani, Daniel W. Peterson, Guy Steele Jr
We formally prove the subject level DP guarantee for our algorithms, and also show their effect on model utility loss.
no code implementations • 12 Mar 2021 • Pallika Kanani, Virendra J. Marathe, Daniel Peterson, Rave Harpaz, Steve Bright
Users can indirectly contribute to, and directly benefit from a much larger aggregate data corpus used to train the global model.
1 code implementation • 13 Oct 2020 • Marcos K. Aguilera, Naama Ben-David, Rachid Guerraoui, Virendra J. Marathe, Athanasios Xygkis, Igor Zablotchi
We propose Mu, a system that takes less than 1. 3 microseconds to replicate a (small) request in memory, and less than a millisecond to fail-over the system - this cuts the replication and fail-over latencies of the prior systems by at least 61% and 90%.
Distributed, Parallel, and Cluster Computing
1 code implementation • 6 Aug 2020 • Rachid Guerraoui, Alex Kogan, Virendra J. Marathe, Igor Zablotchi
Then we present the first algorithm that requires k+1 CASes per call to k-CAS in the common uncontended case.
Distributed, Parallel, and Cluster Computing
no code implementations • 13 Dec 2019 • Daniel Peterson, Pallika Kanani, Virendra J. Marathe
Federated Learning (FL) is a distributed machine learning (ML) paradigm that enables multiple parties to jointly re-train a shared model without sharing their data with any other parties, offering advantages in both scale and privacy.