Search Results for author: Praneeth Vepakomma

Found 24 papers, 5 papers with code

Private measurement of nonlinear correlations between data hosted across multiple parties

no code implementations19 Oct 2021 Praneeth Vepakomma, Subha Nawer Pushpita, Ramesh Raskar

We introduce a differentially private method to measure nonlinear correlations between sensitive data hosted across two entities.

Causal Inference

Parallel Quasi-concave set optimization: A new frontier that scales without needing submodularity

no code implementations19 Aug 2021 Praneeth Vepakomma, Yulia Kempner, Ramesh Raskar

We provide a parallel algorithm with a time complexity over $n$ processors of $\mathcal{O}(n^2g) +\mathcal{O}(\log{\log{n}})$ where $n$ is the cardinality of the ground set and $g$ is the complexity to compute the monotone linkage function that induces a corresponding quasi-concave set function via a duality.

Combinatorial Optimization

AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning

no code implementations2 May 2021 Yusuke Koda, Jihong Park, Mehdi Bennis, Praneeth Vepakomma, Ramesh Raskar

In AirMixML, multiple workers transmit analog-modulated signals of their private data samples to an edge server who trains an ML model using the received noisy-and superpositioned samples.

Data Augmentation

PrivateMail: Supervised Manifold Learning of Deep Features With Differential Privacy for Image Retrieval

no code implementations22 Feb 2021 Praneeth Vepakomma, Julia Balla, Ramesh Raskar

1) We present a novel differentially private method \textit{PrivateMail} for supervised manifold learning, the first of its kind to our knowledge.

Content-Based Image Retrieval

NoPeek: Information leakage reduction to share activations in distributed deep learning

1 code implementation20 Aug 2020 Praneeth Vepakomma, Abhishek Singh, Otkrist Gupta, Ramesh Raskar

For distributed machine learning with sensitive data, we demonstrate how minimizing distance correlation between raw data and intermediary representations reduces leakage of sensitive raw data patterns across client communications while maintaining model accuracy.

SplitNN-driven Vertical Partitioning

no code implementations7 Aug 2020 Iker Ceballos, Vivek Sharma, Eduardo Mugica, Abhishek Singh, Alberto Roman, Praneeth Vepakomma, Ramesh Raskar

In this work, we introduce SplitNN-driven Vertical Partitioning, a configuration of a distributed deep learning method called SplitNN to facilitate learning from vertically distributed features.

Splintering with distributions: A stochastic decoy scheme for private computation

no code implementations6 Jul 2020 Praneeth Vepakomma, Julia Balla, Ramesh Raskar

Performing computations while maintaining privacy is an important problem in todays distributed machine learning solutions.

Privacy in Deep Learning: A Survey

no code implementations25 Apr 2020 Fatemehsadat Mireshghallah, Mohammadkazem Taram, Praneeth Vepakomma, Abhishek Singh, Ramesh Raskar, Hadi Esmaeilzadeh

In this survey, we review the privacy concerns brought by deep learning, and the mitigating techniques introduced to tackle these issues.

Recommendation Systems

Apps Gone Rogue: Maintaining Personal Privacy in an Epidemic

1 code implementation19 Mar 2020 Ramesh Raskar, Isabel Schunemann, Rachel Barbar, Kristen Vilcans, Jim Gray, Praneeth Vepakomma, Suraj Kapa, Andrea Nuzzo, Rajiv Gupta, Alex Berke, Dazza Greenwood, Christian Keegan, Shriank Kanaparti, Robson Beaudry, David Stansbury, Beatriz Botero Arcila, Rishank Kanaparti, Francesco M Benedetti, Alina Clough, Riddhiman Das, Kaushal Jain, Khahlil Louisy, Greg Nadeau, Vitor Pamplona, Steve Penrod, Yasaman Rajaee, Abhishek Singh, Greg Storm, John Werner

Containment, the key strategy in quickly halting an epidemic, requires rapid identification and quarantine of the infected individuals, determination of whom they have had close contact with in the previous days and weeks, and decontamination of locations the infected individual has visited.

Cryptography and Security Computers and Society Distributed, Parallel, and Cluster Computing

Split Learning for collaborative deep learning in healthcare

no code implementations27 Dec 2019 Maarten G. Poirot, Praneeth Vepakomma, Ken Chang, Jayashree Kalpathy-Cramer, Rajiv Gupta, Ramesh Raskar

Shortage of labeled data has been holding the surge of deep learning in healthcare back, as sample sizes are often small, patient information cannot be shared openly, and multi-center collaborative studies are a burden to set up.

Multi-Label Classification

ExpertMatcher: Automating ML Model Selection for Clients using Hidden Representations

no code implementations9 Oct 2019 Vivek Sharma, Praneeth Vepakomma, Tristan Swedish, Ken Chang, Jayashree Kalpathy-Cramer, Ramesh Raskar

Recently, there has been the development of Split Learning, a framework for distributed computation where model components are split between the client and server (Vepakomma et al., 2018b).

Model Selection

Maximal adversarial perturbations for obfuscation: Hiding certain attributes while preserving rest

no code implementations27 Sep 2019 Indu Ilanchezian, Praneeth Vepakomma, Abhishek Singh, Otkrist Gupta, G. N. Srinivasa Prasanna, Ramesh Raskar

In this paper we investigate the usage of adversarial perturbations for the purpose of privacy from human perception and model (machine) based detection.

Data Poisoning

Detailed comparison of communication efficiency of split learning and federated learning

no code implementations18 Sep 2019 Abhishek Singh, Praneeth Vepakomma, Otkrist Gupta, Ramesh Raskar

We compare communication efficiencies of two compelling distributed machine learning approaches of split learning and federated learning.

Federated Learning

Data Markets to support AI for All: Pricing, Valuation and Governance

no code implementations14 May 2019 Ramesh Raskar, Praneeth Vepakomma, Tristan Swedish, Aalekh Sharan

We discuss a data market technique based on intrinsic (relevance and uniqueness) as well as extrinsic value (influenced by supply and demand) of data.

No Peek: A Survey of private distributed deep learning

no code implementations8 Dec 2018 Praneeth Vepakomma, Tristan Swedish, Ramesh Raskar, Otkrist Gupta, Abhimanyu Dubey

We survey distributed deep learning models for training or inference without accessing raw data from clients.

Federated Learning

A Review of Homomorphic Encryption Libraries for Secure Computation

no code implementations6 Dec 2018 Sai Sri Sathya, Praneeth Vepakomma, Ramesh Raskar, Ranjan Ramachandra, Santanu Bhattacharya

In this paper we provide a survey of various libraries for homomorphic encryption.

Cryptography and Security

Optimal bandwidth estimation for a fast manifold learning algorithm to detect circular structure in high-dimensional data

no code implementations28 Dec 2016 Susovan Pal, Praneeth Vepakomma

We provide a way to infer about existence of topological circularity in high-dimensional data sets in $\mathbb{R}^d$ from its projection in $\mathbb{R}^2$ obtained through a fast manifold learning map as a function of the high-dimensional dataset $\mathbb{X}$ and a particular choice of a positive real $\sigma$ known as bandwidth parameter.

Supervised Dimensionality Reduction via Distance Correlation Maximization

no code implementations3 Jan 2016 Praneeth Vepakomma, Chetan Tonde, Ahmed Elgammal

In our work, we propose a novel formulation for supervised dimensionality reduction based on a nonlinear dependency criterion called Statistical Distance Correlation, Szekely et.

Supervised dimensionality reduction

DISCOMAX: A Proximity-Preserving Distance Correlation Maximization Algorithm

no code implementations11 Jun 2013 Praneeth Vepakomma, Ahmed Elgammal

Our setting is different from subset-selection algorithms where the problem is to choose the best subset of features for regression.

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