Past Member

Praneeth Vepakomma

Former Research Assistant

Contact Information:

Groups

Publication

Posthoc privacy guarantees for collaborative inference with modified Propose-Test-Release

Singh, Abhishek, et al. "Posthoc privacy guarantees for collaborative inference with modified Propose-Test-Release." Thirty-seventh Conference on Neural Information Processing Systems. 2023.

Publication

Parallel quasi-concave set function optimization for scalability even without submodularity

Publication

Visual Transformer Meets CutMix for Improved Accuracy, Communication Efficiency, and Data Privacy in Split Learning

Publication

Formal privacy guarantees for neural network queries by estimating local Lipschitz constant

Formal Privacy Guarantees for Neural Network queries by estimating local Lipschitz constant

Publication

Private independence testing across two parties

Publication

Effects of Privacy-Inducing Noise on Welfare and Influence of Referendum Systems

Suat Evren, Praneeth Vepakomma

Publication

NoPeek-Infer: Preventing face reconstruction attacks in distributed inference after on-premise training

Praneeth Vepakomma, Abhishek Singh, Emily Zhang, Otkrist Gupta, Ramesh Raskar, IEEE International Conference on Automatic Face and Gesture Recognition (FG) 2021

Publication

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

IEEE Global Communications Conference (GLOBECOM), 2021

Publication

Differentially Private Supervised Manifold Learning with Applications like Private Image Retrieval

Vepakomma, Praneeth et al. Differentially Private Supervised Manifold Learning with Applications like Private Image Retrieval. arXiv:2102.10802v1 [cs.LG] 22 Feb 2021

Publication

FedML: A Research Library and Benchmark for Federated Machine Learning

Chaoyang He, Songze Li, Jinhyun So, Mi Zhang, Xiao Zeng, Hongyi Wang, Xiaoyang Wang, Praneeth Vepakomma, Abhishek Singh, Hang Qiu, Xinghua Zhu, Jianzong Wang, Li Shen, Peilin Zhao, Yan Kang, Yang Liu, Ramesh Raskar, Qiang Yang, Murali Annavaram and Salman Avestimehr. "FedML: A Research Library and Benchmark for Federated Machine Learning." NeurIPS-SpicyFL 2020. (Baidu Best Paper Award)

Publication

DAMS: Meta-estimation of private sketch data structures for differentially private COVID-19 contact tracing

DAMS: Meta-estimation of private sketch data structures for differentially private COVID-19 contact tracing, Praneeth Vepakomma, Subha Nawer Pushpita and Ramesh Raskar, PPML (Privacy Preserving Machine Learning workshop) at NeurIPS

Publication

DISCO: Dynamic and Invariant Sensitive Channel Obfuscation

Abhishek Singh, Ayush Chopra, Praneeth Vepakomma, Ethan Z Garza, Vivek Sharma, , Ramesh Raskar. "DISCO: Dynamic and Invariant Sensitive Channel Obfuscation." CVPR 2021

Publication

Splintering with distributions: A stochastic decoy scheme for private computation

Vepakomma, P., Balla, J., Raskar, R., "Splintering with distributions: A stochastic decoy scheme for private computation." 6 Jul 2020.

Publication

Assessing Disease Exposure Risk with Location Data: A Proposal for Cryptographic Preservation of Privacy

Alex Berke, Michiel Bakker, Praneeth Vepakomma, Kent Larson, Alex `Sandy' Pentland. (March 31 2020). "Assessing Disease Exposure Risk with Location Data: A Proposal for Cryptographic Preservation of Privacy." Retrieved from https://arxiv.org/pdf/2003.14412

Publication

Advances and Open Problems in Federated Learning

Peter Kairouz, H. Brendan McMahan, et al. "Advances and Open Problems in Federated Learning." arXiv:1912.04977 [cs.LG] 10 Dec 2019.

Publication

ExpertMatcher: Automating ML Model Selection for Clients using Hidden Representations

Vivek Sharma, Praneeth Vepakomma, Tristan Swedish, Ken Chang, Jayashree KalpathyCramer, and Ramesh Raskar. In NeurIPS Workshop on Robust AI in Financial Services: Data, Fairness, Explainability, Trustworthiness, and Privacy, 2019

Publication

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

Indu Ilanchezian, Praneeth Vepakomma, Abhishek Singh, Otkrist Gupta, GN Prasanna, Ramesh Raskar

Publication

ExpertMatcher: Automating ML Model Selection for Users in Resource Constrained Countries

Vivek Sharma, Praneeth Vepakomma, Tristan Swedish, Ken Chang, Jayashree Kalpathy-Cramer, Ramesh Raskar. In NeurIPS Workshop on Machine learning for the Developing World (ML4D), 2019

Publication

Detailed comparison of communication efficiency of split learning and federated learning,

Praneeth Vepakomma, et al. "Detailed comparison of communication efficiency of split learning and federated learning." arXiv:1909.09145v1 [cs.LG] 18 Sep 2019.

Publication

Diverse data selection via combinatorial quasi-concavity of distance covariance: A polynomial time global minimax algorithm

Diverse data selection via combinatorial quasi-concavity of distance covariance: A polynomial time global minimax algorithm, Praneeth Vepakomma, Yulia Kempner

Publication

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

Ramesh Raskar, Praneeth Vepakomma, Tristan Swedish, Aalekh Sharan. Data Markets to support AI for All: Pricing, Valuation and Governance, arXiv:1905.06462 (2019).

Publication

A Review of Homomorphic Encryption Libraries for Secure Computation

Sai Sri Sathya, Praneeth Vepakomma, Ramesh Raskar, Ranjan Ramachandra, Santanu Bhattacharya. arXiv:1812.02428

Publication

Split learning for health: Distributed deep learning without sharing raw patient data

Praneeth Vepakomma, et al. "Split learning for health: Distributed deep learning without sharing raw patient data." arXiv:1812.00564v1 [cs.LG] 3 Dec 2018.

Publication

Supervised Dimensionality Reduction via Distance Correlation Maximization

Electronic Journal of Statistics, volume 12 No.1, Pages 960--984, The Institute of Mathematical Statistics and the Bernoulli Society, 2018

Publication

Combinatorics of Distance Covariance: Inclusion-Minimal Maximizers of Quasi-Concave Set Functions for Diverse Variable Selection

Publication

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

Publication

A Fast Algorithm for Manifold Learning by Posing it as a Symmetric Diagonally Dominant Linear System

Applied and Computational Harmonic Analysis