Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Abhradeep Thakurta

Practical and Private (Deep) Learning without Sampling or Shuffling


Feb 26, 2021
Peter Kairouz, Brendan McMahan, Shuang Song, Om Thakkar, Abhradeep Thakurta, Zheng Xu


  Access Paper or Ask Questions

Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning


Jan 11, 2021
Milad Nasr, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, Nicholas Carlini


  Access Paper or Ask Questions

An Attack on InstaHide: Is Private Learning Possible with Instance Encoding?


Nov 10, 2020
Nicholas Carlini, Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Shuang Song, Abhradeep Thakurta, Florian Tramer


  Access Paper or Ask Questions

Dimension Independence in Unconstrained Private ERM via Adaptive Preconditioning


Aug 14, 2020
Peter Kairouz, Mónica Ribero, Keith Rush, Abhradeep Thakurta


  Access Paper or Ask Questions

Privacy Amplification via Random Check-Ins


Jul 30, 2020
Borja Balle, Peter Kairouz, H. Brendan McMahan, Om Thakkar, Abhradeep Thakurta

* Updated proof for $(\epsilon_0, \delta_0)$-DP local randomizers 

  Access Paper or Ask Questions

Tempered Sigmoid Activations for Deep Learning with Differential Privacy


Jul 28, 2020
Nicolas Papernot, Abhradeep Thakurta, Shuang Song, Steve Chien, Úlfar Erlingsson


  Access Paper or Ask Questions

Characterizing Private Clipped Gradient Descent on Convex Generalized Linear Problems


Jun 11, 2020
Shuang Song, Om Thakkar, Abhradeep Thakurta


  Access Paper or Ask Questions

Obliviousness Makes Poisoning Adversaries Weaker


Mar 26, 2020
Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Abhradeep Thakurta


  Access Paper or Ask Questions

Private Stochastic Convex Optimization with Optimal Rates


Aug 27, 2019
Raef Bassily, Vitaly Feldman, Kunal Talwar, Abhradeep Thakurta


  Access Paper or Ask Questions

Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity


Nov 29, 2018
Úlfar Erlingsson, Vitaly Feldman, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, Abhradeep Thakurta


  Access Paper or Ask Questions

Privacy Amplification by Iteration


Aug 20, 2018
Vitaly Feldman, Ilya Mironov, Kunal Talwar, Abhradeep Thakurta

* Extended abstract appears in Foundations of Computer Science (FOCS) 2018 

  Access Paper or Ask Questions

Differentially Private Matrix Completion Revisited


Jun 12, 2018
Prateek Jain, Om Thakkar, Abhradeep Thakurta

* Updated version. Accepted for presentation at International Conference on Machine Learning (ICML) 2018 

  Access Paper or Ask Questions

Model-Agnostic Private Learning via Stability


Mar 14, 2018
Raef Bassily, Om Thakkar, Abhradeep Thakurta


  Access Paper or Ask Questions

Private Empirical Risk Minimization Beyond the Worst Case: The Effect of the Constraint Set Geometry


Nov 20, 2016
Kunal Talwar, Abhradeep Thakurta, Li Zhang


  Access Paper or Ask Questions

To Drop or Not to Drop: Robustness, Consistency and Differential Privacy Properties of Dropout


Mar 06, 2015
Prateek Jain, Vivek Kulkarni, Abhradeep Thakurta, Oliver Williams

* Currently under review for ICML 2015 

  Access Paper or Ask Questions

Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds


Oct 17, 2014
Raef Bassily, Adam Smith, Abhradeep Thakurta


  Access Paper or Ask Questions

Differentially Private Online Learning


Sep 16, 2011
Prateek Jain, Pravesh Kothari, Abhradeep Thakurta


  Access Paper or Ask Questions