Shield: Secure Allegation Escrow System with Stronger Guarantees

April 2023 Shield: Secure Allegation Escrow System with Stronger Guarantees Authors: Koti, N., Kukkala, V. B., Patra, A., & Gopal, B. R The rising issues of harassment, exploitation, corruption, and other forms of abuse have led victims to seek comfort by acting in unison against common perpetrators (e.g., #MeToo movement). One way to curb these issues is to install allegation …

Continue Reading

Find thy neighbourhood: Privacy-preserving local clustering.

December 2022 Find thy neighbourhood: Privacy-preserving local clustering Authors: Koti, Nishat, Varsha Bhat Kukkala, Arpita Patra, and Bhavish Raj Gopal Identifying a cluster around a seed node in a graph, termed local clustering, finds use in several applications, including fraud detection, targeted advertising, community detection, etc. However, performing local clustering is challenging when the graph is distributed among multiple data …

Continue Reading

Pentagod: Stepping beyond traditional god with five parties

Aug 2022 Pentagod: Stepping beyond traditional god with five parties Authors: Koti, N., Kukkala, V. B., Patra, A., & Raj Gopal, B. Secure multiparty computation (MPC) is increasingly being used to address privacy issues in various applications. The recent work of Alon et al. (CRYPTO’20) identified the shortcomings of traditional MPC and defined a Friends-and-Foes (FaF) security notion to address …

Continue Reading

Performance Characterization of Containerized DNN Training and Inference on Edge Accelerators

December 2023 Performance Characterization of Containerized DNN Training and Inference on Edge Accelerators Authors: Prashanthi S.K., Vinayaka Hegde, Keerthana Patchava, Ankita Das and Yogesh Simmhan Edge devices have typically been used for DNN in-ferencing. The increase in the compute power of accelerated edges is leading to their use in DNN training also. As privacy becomes a concern on multi-tenant edge …

Continue Reading

Optimizing Federated Learning using Remote Embeddings for Graph Neural Networks

Aug 2024 Optimizing Federated Learning using Remote Embeddings for Graph Neural Networks Authors: Pranjal Naman and Yogesh Simmhan, Graph Neural Networks (GNNs) have experienced rapid advancements in recent years due to their ability to learn meaningful representations from graph data structures. Federated Learning (FL) has emerged as a viable machine learning approach for training a shared model on decentralized data, addressing privacy concerns while leveraging …

Continue Reading

Minimizing Layerwise Activation Norm Improves Generalization in Federated Learning

April 2024 Minimizing Layerwise Activation Norm Improves Generalization in Federated Learning Authors: M. Yashwanth, G. K. Nayak, H. Rangwani, A. Singh, R. V. Babu, A. Chakraborty Federated Learning (FL) is an emerging machine learning framework that enables multiple clients (coordinated by a server) to collaboratively train a global model by aggregating the locally trained models without sharing any client’s training data. …

Continue Reading

Continual Mean Estimation Under User-Level Privacy

December 2022 Continual Mean Estimation Under User-Level Privacy Authors: A. J. George, L. Ramesh, A. V. Singh and H. Tyagi We consider the problem of continually releasing an estimate of the population mean of a stream of samples that is user-level differentially private (DP). At each time instant, a user contributes a sample, and the users can arrive in arbitrary …

Continue Reading

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