Search Results for author: Ismat Jarin

Found 4 papers, 2 papers with code

Maverick-Aware Shapley Valuation for Client Selection in Federated Learning

no code implementations21 May 2024 Mengwei Yang, Ismat Jarin, Baturalp Buyukates, Salman Avestimehr, Athina Markopoulou

In this paper, we first design a Maverick-aware Shapley valuation that fairly evaluates the contribution of Mavericks.

Federated Learning

MIAShield: Defending Membership Inference Attacks via Preemptive Exclusion of Members

no code implementations2 Mar 2022 Ismat Jarin, Birhanu Eshete

In membership inference attacks (MIAs), an adversary observes the predictions of a model to determine whether a sample is part of the model's training data.

Image Classification Knowledge Distillation

DP-UTIL: Comprehensive Utility Analysis of Differential Privacy in Machine Learning

1 code implementation24 Dec 2021 Ismat Jarin, Birhanu Eshete

In this paper, we present, DP-UTIL, a holistic utility analysis framework of DP across the ML pipeline with focus on input perturbation, objective perturbation, gradient perturbation, output perturbation, and prediction perturbation.

BIG-bench Machine Learning Inference Attack +2

PRICURE: Privacy-Preserving Collaborative Inference in a Multi-Party Setting

1 code implementation19 Feb 2021 Ismat Jarin, Birhanu Eshete

This paper presents PRICURE, a system that combines complementary strengths of secure multi-party computation (SMPC) and differential privacy (DP) to enable privacy-preserving collaborative prediction among multiple model owners.

Collaborative Inference Image Classification +4

Cannot find the paper you are looking for? You can Submit a new open access paper.