collaborators

5 papers

cs.CR2026

Conformal-DP: A Density-Aware Mechanism for Differential Privacy over Riemannian Manifolds via Conformal Transformation

Peilin He, Liou Tang, M. Amin Rahimian +1

Differential Privacy (DP) is being increasingly adopted for non-Euclidean data that lie on complex, high-dimensional manifolds. Existing DP mechanisms for manifold data consider ge…

cs.CR2026

Sparsification Under Siege: Dual-Level Defense Against Poisoning in Communication-Efficient Federated Learning

Zhiyong Jin, Runhua Xu, Chao Li +3

Gradient sparsification, while mitigating communication bottlenecks in Federated Learning (FL), fundamentally alters the geometric landscape of model updates. We reveal that the re…

cs.CR2026

Privacy at Scale in Networked Healthcare

M. Amin Rahimian, Benjamin Panny, James Joshi

Digitized, networked healthcare promises earlier detection, precision therapeutics, and continuous care; yet, it also expands the surface for privacy loss and compliance risk. We a…

cs.LG2025

PPFL-RDSN: Privacy-Preserving Federated Learning-based Residual Dense Spatial Networks for Encrypted Lossy Image Reconstruction

Peilin He, James Joshi

Reconstructing high-quality images from low-resolution inputs using Residual Dense Spatial Networks (RDSNs) is crucial yet challenging. It is even more challenging in centralized t…

cs.LG2025

Apollo: A Posteriori Label-Only Membership Inference Attack Towards Machine Unlearning

Liou Tang, James Joshi, Ashish Kundu

Machine Unlearning (MU) aims to update Machine Learning (ML) models following requests to remove training samples and their influences on a trained model efficiently without retrai…