activity
20182022
most citedGazelle: A Low Latency Framework for Secure Neural Network Inference

175 citations · 188 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CR20212 cited

NeuraCrypt: Hiding Private Health Data via Random Neural Networks for Public Training

Adam Yala, Homa Esfahanizadeh, Rafael G. L. D' Oliveira +6

Balancing the needs of data privacy and predictive utility is a central challenge for machine learning in healthcare. In particular, privacy concerns have led to a dearth of public…

quant-ph20202 cited

Oblivious Transfer is in MiniQCrypt

Alex B. Grilo, Huijia Lin, Fang Song +1

MiniQCrypt is a world where quantum-secure one-way functions exist, and quantum communication is possible. We construct an oblivious transfer (OT) protocol in MiniQCrypt that achie…

cs.CC2020

On the Hardness of Average-case k-SUM

Zvika Brakerski, Noah Stephens-Davidowitz, Vinod Vaikuntanathan

In this work, we show the first worst-case to average-case reduction for the classical -SUM problem. A -SUM instance is a collection of integers, and the goal of the -…

stat.ML20197 cited

Computational Limitations in Robust Classification and Win-Win Results

Akshay Degwekar, Preetum Nakkiran, Vinod Vaikuntanathan

We continue the study of statistical/computational tradeoffs in learning robust classifiers, following the recent work of Bubeck, Lee, Price and Razenshteyn who showed examples of…

cs.CR2018

How to Subvert Backdoored Encryption: Security Against Adversaries that Decrypt All Ciphertexts

Thibaut Horel, Sunoo Park, Silas Richelson +1

We study secure and undetectable communication in a world where governments can read all encrypted communications of citizens. We consider a world where the only permitted communic…

cs.CR2018175 cited

Gazelle: A Low Latency Framework for Secure Neural Network Inference

Chiraag Juvekar, Vinod Vaikuntanathan, Anantha Chandrakasan

The growing popularity of cloud-based machine learning raises a natural question about the privacy guarantees that can be provided in such a setting. Our work tackles this problem…