activity
20242026
collaborators

5 papers

cs.IT2026

Bounding User Contributions for User-Level Differentially Private Mean Estimation

V. Arvind Rameshwar, Anshoo Tandon

We revisit the problem of releasing the sample mean of bounded samples in a dataset, privately, under user-level -differential privacy (DP). We aim to derive the optim…

cs.IT2025

-Diversity: Linkage-Robustness via a Composition Theorem

V. Arvind Rameshwar, Anshoo Tandon

In this paper, we consider the problem of degradation of anonymity upon linkages of anonymized datasets. We work in the setting where an adversary links together anonymiz…

cs.CR2025

On Improving the Composition Privacy Loss in Differential Privacy for Fixed Estimation Error

V. Arvind Rameshwar, Anshoo Tandon

This paper considers the private release of statistics of disjoint subsets of a dataset, in the setting of data heterogeneity, where users could contribute more than one sample, wi…

cs.CR2024

Enhancing MOTION2NX for Efficient, Scalable and Secure Image Inference using Convolutional Neural Networks

Haritha K, Ramya Burra, Srishti Mittal +3

This work contributes towards the development of an efficient and scalable open-source Secure Multi-Party Computation (SMPC) protocol on machines with moderate computational resour…

cs.IT2024

Optimal Tree-Based Mechanisms for Differentially Private Approximate CDFs

V. Arvind Rameshwar, Anshoo Tandon, Abhay Sharma

This paper considers the -differentially private (DP) release of an approximate cumulative distribution function (CDF) of the samples in a dataset. We assume that the…