Search Results for author: Raksha Ramakrishna

Found 4 papers, 0 papers with code

Differential Privacy for Class-based Data: A Practical Gaussian Mechanism

no code implementations8 Jun 2023 Raksha Ramakrishna, Anna Scaglione, Tong Wu, Nikhil Ravi, Sean Peisert

In this paper, we present a notion of differential privacy (DP) for data that comes from different classes.

Inferring Class Label Distribution of Training Data from Classifiers: An Accuracy-Augmented Meta-Classifier Attack

no code implementations8 Nov 2022 Raksha Ramakrishna, György Dán

In this paper we introduce a new type of property inference attack that unlike binary decision problems in literature, aim at inferring the class label distribution of the training data from parameters of ML classifier models.

Inference Attack

Grid-Graph Signal Processing (Grid-GSP): A Graph Signal Processing Framework for the Power Grid

no code implementations10 Mar 2021 Raksha Ramakrishna, Anna Scaglione

The underlying theme of this paper is to explore the various facets of power systems data through the lens of graph signal processing (GSP), laying down the foundations of the Grid-GSP framework.

Data Compression

A User Guide to Low-Pass Graph Signal Processing and its Applications

no code implementations4 Aug 2020 Raksha Ramakrishna, Hoi-To Wai, Anna Scaglione

The notion of graph filters can be used to define generative models for graph data.

Cannot find the paper you are looking for? You can Submit a new open access paper.