Alert button
Picture for Chiyuan Zhang

Chiyuan Zhang

Alert button

Training Differentially Private Ad Prediction Models with Semi-Sensitive Features

Jan 26, 2024
Lynn Chua, Qiliang Cui, Badih Ghazi, Charlie Harrison, Pritish Kamath, Walid Krichene, Ravi Kumar, Pasin Manurangsi, Krishna Giri Narra, Amer Sinha, Avinash Varadarajan, Chiyuan Zhang

Viaarxiv icon

Optimal Unbiased Randomizers for Regression with Label Differential Privacy

Dec 09, 2023
Ashwinkumar Badanidiyuru, Badih Ghazi, Pritish Kamath, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Avinash V Varadarajan, Chiyuan Zhang

Viaarxiv icon

Sparsity-Preserving Differentially Private Training of Large Embedding Models

Nov 14, 2023
Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang

Figure 1 for Sparsity-Preserving Differentially Private Training of Large Embedding Models
Figure 2 for Sparsity-Preserving Differentially Private Training of Large Embedding Models
Figure 3 for Sparsity-Preserving Differentially Private Training of Large Embedding Models
Figure 4 for Sparsity-Preserving Differentially Private Training of Large Embedding Models
Viaarxiv icon

User-Level Differential Privacy With Few Examples Per User

Sep 21, 2023
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Raghu Meka, Chiyuan Zhang

Figure 1 for User-Level Differential Privacy With Few Examples Per User
Figure 2 for User-Level Differential Privacy With Few Examples Per User
Viaarxiv icon

Can Neural Network Memorization Be Localized?

Jul 18, 2023
Pratyush Maini, Michael C. Mozer, Hanie Sedghi, Zachary C. Lipton, J. Zico Kolter, Chiyuan Zhang

Figure 1 for Can Neural Network Memorization Be Localized?
Figure 2 for Can Neural Network Memorization Be Localized?
Figure 3 for Can Neural Network Memorization Be Localized?
Figure 4 for Can Neural Network Memorization Be Localized?
Viaarxiv icon

Ticketed Learning-Unlearning Schemes

Jun 27, 2023
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Ayush Sekhari, Chiyuan Zhang

Figure 1 for Ticketed Learning-Unlearning Schemes
Figure 2 for Ticketed Learning-Unlearning Schemes
Figure 3 for Ticketed Learning-Unlearning Schemes
Figure 4 for Ticketed Learning-Unlearning Schemes
Viaarxiv icon

On User-Level Private Convex Optimization

May 08, 2023
Badih Ghazi, Pritish Kamath, Ravi Kumar, Raghu Meka, Pasin Manurangsi, Chiyuan Zhang

Figure 1 for On User-Level Private Convex Optimization
Viaarxiv icon

Regression with Label Differential Privacy

Dec 12, 2022
Badih Ghazi, Pritish Kamath, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Avinash Varadarajan, Chiyuan Zhang

Figure 1 for Regression with Label Differential Privacy
Figure 2 for Regression with Label Differential Privacy
Figure 3 for Regression with Label Differential Privacy
Figure 4 for Regression with Label Differential Privacy
Viaarxiv icon

Private Ad Modeling with DP-SGD

Nov 21, 2022
Carson Denison, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Krishna Giri Narra, Amer Sinha, Avinash Varadarajan, Chiyuan Zhang

Figure 1 for Private Ad Modeling with DP-SGD
Figure 2 for Private Ad Modeling with DP-SGD
Figure 3 for Private Ad Modeling with DP-SGD
Figure 4 for Private Ad Modeling with DP-SGD
Viaarxiv icon

Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy

Oct 31, 2022
Daphne Ippolito, Florian Tramèr, Milad Nasr, Chiyuan Zhang, Matthew Jagielski, Katherine Lee, Christopher A. Choquette-Choo, Nicholas Carlini

Figure 1 for Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy
Figure 2 for Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy
Figure 3 for Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy
Figure 4 for Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy
Viaarxiv icon