collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2025

High-Dimensional Privacy-Utility Dynamics of Noisy Stochastic Gradient Descent on Least Squares

Shurong Lin, Eric D. Kolaczyk, Adam Smith +1

The interplay between optimization and privacy has become a central theme in privacy-preserving machine learning. Noisy stochastic gradient descent (SGD) has emerged as a cornersto…

cs.LG2025

The Sample Complexity of Membership Inference and Privacy Auditing

Mahdi Haghifam, Adam Smith, Jonathan Ullman

A membership-inference attack gets the output of a learning algorithm, and a target individual, and tries to determine whether this individual is a member of the training data or a…

cs.LG2025

Black-Box Privacy Attacks on Shared Representations in Multitask Learning

John Abascal, Nicolás Berrios, Alina Oprea +3

Multitask learning (MTL) has emerged as a powerful paradigm that leverages similarities among multiple learning tasks, each with insufficient samples to train a standalone model, t…

cs.LG2024

Privacy in Metalearning and Multitask Learning: Modeling and Separations

Maryam Aliakbarpour, Konstantina Bairaktari, Adam Smith +2

Model personalization allows a set of individuals, each facing a different learning task, to train models that are more accurate for each person than those they could develop indiv…

cs.LG2024

Auditing Privacy Mechanisms via Label Inference Attacks

Róbert István Busa-Fekete, Travis Dick, Claudio Gentile +3

We propose reconstruction advantage measures to audit label privatization mechanisms. A reconstruction advantage measure quantifies the increase in an attacker's ability to infer t…