activity
20192022
most citedBackpropagation Clipping for Deep Learning with Differential Privacy

3 citations · 7 across the 6 of their papers we have counts for

collaborators

13 papers

cs.CR2025

SMT-Boosted Security Types for Low-Level MPC

Christian Skalka, Joseph P. Near

Secure Multi-Party Computation (MPC) is an important enabling technology for data privacy in modern distributed applications. We develop a new type theory to automatically enforce…

cs.CR20221 cited

Improving Utility for Privacy-Preserving Analysis of Correlated Columns using Pufferfish Privacy

Krystal Maughan, Joseph P. Near

Surveys are an important tool for many areas of social science research, but privacy concerns can complicate the collection and analysis of survey data. Differentially private anal…

cs.LG20223 cited

Backpropagation Clipping for Deep Learning with Differential Privacy

Timothy Stevens, Ivoline C. Ngong, David Darais +3

We present backpropagation clipping, a novel variant of differentially private stochastic gradient descent (DP-SGD) for privacy-preserving deep learning. Our approach clips each tr…

cs.LG2022

Prediction Sensitivity: Continual Audit of Counterfactual Fairness in Deployed Classifiers

Krystal Maughan, Ivoline C. Ngong, Joseph P. Near

As AI-based systems increasingly impact many areas of our lives, auditing these systems for fairness is an increasingly high-stakes problem. Traditional group fairness metrics can…

cs.CR20211 cited

Do I Get the Privacy I Need? Benchmarking Utility in Differential Privacy Libraries

Gonzalo Munilla Garrido, Joseph Near, Aitsam Muhammad +3

An increasing number of open-source libraries promise to bring differential privacy to practice, even for non-experts. This paper studies five libraries that offer differentially p…

cs.PL2021

Solo: A Lightweight Static Analysis for Differential Privacy

Chike Abuah, David Darais, Joseph P. Near

All current approaches for statically enforcing differential privacy in higher order languages make use of either linear or relational refinement types. A barrier to adoption for t…