User-Level Differentially Private Mean Estimation for Real-World Datasets

User-Level Differentially Private Mean Estimation for Real-World Datasets Authors: V. A. Rameshwar, A. Tandon, and A. Sharma In this work, we provide rigorous theoretical justifications for the performance trends of well-known clipping-based algorithms on real-world ITMS and i.i.d. synthetic datasets. An important contribution of this work is the formalization and explicit computation of the “worst-case estimation error” incurred by a …

Continue Reading

Empowering SMPC: Bridging the Gap Between Scalability, Memory Efficiency and Privacy in Neural Network Inference

Jan 2024 Empowering SMPC: Bridging the Gap Between Scalability, Memory Efficiency and Privacy in Neural Network Inference Authors: R. Burra, A. Tandon and S. Mittal This paper aims to develop an efficient open-source Secure Multi-Party Computation (SMPC) repository, that addresses the issue of practical and scalable implementation of SMPC protocol on machines with moderate computational resources while aiming to reduce …

Continue Reading

Mean Estimation with User-Level Privacy for Spatio-Temporal IoT Datasets

April 2024 Mean Estimation with User-Level Privacy for Spatio-Temporal IoT Datasets Authors: P. Gupta, V. A. Rameshwar, A. Tandon and N. Chakraborty This paper considers the problem of the private release of sample means of speed values from traffic datasets. Our key contribution is the development of user-level differentially private algorithms that incorporate carefully chosen parameter values to ensure low …

Continue Reading