Publications ›› Papers ›› Data Privacy

Graphiti: Secure Graph Computation Made More Scalable

Authors: Koti, N., Kukkala, V. B., Patra, A., & Raj Gopal, B. Know more Privacy-preserving graph analysis allows performing computations on graphs that store sensitive information, while ensuring all the information about the topology of the graph as well as data associated with the nodes and edges remains hidden. The current work addresses this problem […]

Ruffle: Rapid 3-party shuffle protocols

Authors: Koti, N., Kukkala, V. B., Patra, A., Gopal, B. R., & Sangal, S Know more Secure shuffle is an important primitive that finds use in several applications such as secure electronic voting, oblivious RAMs, secure sorting, to name a few. For time-sensitive shuffle-based applications that demand a fast response time, it is essential to […]

Vogue: Faster computation of private heavy hitters

Authors: Jangir, P., Koti, N., Kukkala, V. B., Patra, A., Gopal, B. R., & Sangal, S Know more Consider the problem of securely identifying τ -heavy hitters, where given a set of client inputs, the goal is to identify those inputs which are held by at least τ clients in a privacy-preserving manner. Towards this, […]

Shield: Secure Allegation Escrow System with Stronger Guarantees

Authors: Koti, N., Kukkala, V. B., Patra, A., & Gopal, B. R Know more 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 escrow systems that […]

Find thy neighbourhood: Privacy-preserving local clustering.

Authors: Koti, Nishat, Varsha Bhat Kukkala, Arpita Patra, and Bhavish Raj Gopal Know more 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 owners, […]

Pentagod: Stepping beyond traditional god with five parties

Authors: Koti, N., Kukkala, V. B., Patra, A., & Raj Gopal, B. Know more 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 the same. We […]

Optimizing Federated Learning using Remote Embeddings for Graph Neural Networks

Authors: Pranjal Naman and Yogesh Simmhan, Know more 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 parallelism. Existing methods that address […]

Minimizing Layerwise Activation Norm Improves Generalization in Federated Learning

Authors: M. Yashwanth, G. K. Nayak, H. Rangwani, A. Singh, R. V. Babu, A. Chakraborty Know more 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. It has been observed […]

Continual Mean Estimation Under User-Level Privacy

Authors: A. J. George, L. Ramesh, A. V. Singh and H. Tyagi Know more 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 order. […]

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

Authors: V. A. Rameshwar, A. Tandon, and A. Sharma Know more 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 canonical […]