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 Thomas Steinke

Thomas Steinke
Alert button

Why Is Public Pretraining Necessary for Private Model Training?


Feb 19, 2023
Arun Ganesh, Mahdi Haghifam, Milad Nasr, Sewoong Oh, Thomas Steinke, Om Thakkar, Abhradeep Thakurta, Lun Wang

Add code
Alert button

Figure 1 for Why Is Public Pretraining Necessary for Private Model Training?
Figure 2 for Why Is Public Pretraining Necessary for Private Model Training?
Figure 3 for Why Is Public Pretraining Necessary for Private Model Training?
Figure 4 for Why Is Public Pretraining Necessary for Private Model Training?

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Tight Auditing of Differentially Private Machine Learning


Feb 15, 2023
Milad Nasr, Jamie Hayes, Thomas Steinke, Borja Balle, Florian Tramèr, Matthew Jagielski, Nicholas Carlini, Andreas Terzis

Add code
Alert button

Figure 1 for Tight Auditing of Differentially Private Machine Learning
Figure 2 for Tight Auditing of Differentially Private Machine Learning
Figure 3 for Tight Auditing of Differentially Private Machine Learning
Figure 4 for Tight Auditing of Differentially Private Machine Learning

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A Bias-Variance-Privacy Trilemma for Statistical Estimation


Jan 30, 2023
Gautam Kamath, Argyris Mouzakis, Matthew Regehr, Vikrant Singhal, Thomas Steinke, Jonathan Ullman

Add code
Alert button


   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Composition of Differential Privacy & Privacy Amplification by Subsampling


Oct 04, 2022
Thomas Steinke

Add code
Alert button

Figure 1 for Composition of Differential Privacy & Privacy Amplification by Subsampling
Figure 2 for Composition of Differential Privacy & Privacy Amplification by Subsampling

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Algorithms with More Granular Differential Privacy Guarantees


Sep 08, 2022
Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Thomas Steinke

Add code
Alert button

Figure 1 for Algorithms with More Granular Differential Privacy Guarantees

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Debugging Differential Privacy: A Case Study for Privacy Auditing


Mar 28, 2022
Florian Tramer, Andreas Terzis, Thomas Steinke, Shuang Song, Matthew Jagielski, Nicholas Carlini

Add code
Alert button

Figure 1 for Debugging Differential Privacy: A Case Study for Privacy Auditing

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Public Data-Assisted Mirror Descent for Private Model Training


Dec 01, 2021
Ehsan Amid, Arun Ganesh, Rajiv Mathews, Swaroop Ramaswamy, Shuang Song, Thomas Steinke, Vinith M. Suriyakumar, Om Thakkar, Abhradeep Thakurta

Add code
Alert button

Figure 1 for Public Data-Assisted Mirror Descent for Private Model Training
Figure 2 for Public Data-Assisted Mirror Descent for Private Model Training
Figure 3 for Public Data-Assisted Mirror Descent for Private Model Training
Figure 4 for Public Data-Assisted Mirror Descent for Private Model Training
* 20 pages, 9 figures, 3 tables 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A Private and Computationally-Efficient Estimator for Unbounded Gaussians


Nov 08, 2021
Gautam Kamath, Argyris Mouzakis, Vikrant Singhal, Thomas Steinke, Jonathan Ullman

Add code
Alert button

Figure 1 for A Private and Computationally-Efficient Estimator for Unbounded Gaussians

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Hyperparameter Tuning with Renyi Differential Privacy


Oct 07, 2021
Nicolas Papernot, Thomas Steinke

Add code
Alert button

Figure 1 for Hyperparameter Tuning with Renyi Differential Privacy
Figure 2 for Hyperparameter Tuning with Renyi Differential Privacy
Figure 3 for Hyperparameter Tuning with Renyi Differential Privacy
Figure 4 for Hyperparameter Tuning with Renyi Differential Privacy

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
>>