Picture for Jamie Hayes

Jamie Hayes

Locking Machine Learning Models into Hardware

Add code
May 31, 2024
Viaarxiv icon

Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy

Mar 02, 2024
Figure 1 for Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy
Figure 2 for Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy
Figure 3 for Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy
Figure 4 for Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy
Viaarxiv icon

Buffer Overflow in Mixture of Experts

Feb 08, 2024
Viaarxiv icon

Unlocking Accuracy and Fairness in Differentially Private Image Classification

Add code
Aug 21, 2023
Figure 1 for Unlocking Accuracy and Fairness in Differentially Private Image Classification
Figure 2 for Unlocking Accuracy and Fairness in Differentially Private Image Classification
Figure 3 for Unlocking Accuracy and Fairness in Differentially Private Image Classification
Figure 4 for Unlocking Accuracy and Fairness in Differentially Private Image Classification
Viaarxiv icon

Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacy

Jul 08, 2023
Figure 1 for Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacy
Figure 2 for Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacy
Figure 3 for Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacy
Figure 4 for Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacy
Viaarxiv icon

Differentially Private Diffusion Models Generate Useful Synthetic Images

Feb 27, 2023
Figure 1 for Differentially Private Diffusion Models Generate Useful Synthetic Images
Figure 2 for Differentially Private Diffusion Models Generate Useful Synthetic Images
Figure 3 for Differentially Private Diffusion Models Generate Useful Synthetic Images
Figure 4 for Differentially Private Diffusion Models Generate Useful Synthetic Images
Viaarxiv icon

Tight Auditing of Differentially Private Machine Learning

Add code
Feb 15, 2023
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
Viaarxiv icon

Bounding Training Data Reconstruction in DP-SGD

Add code
Feb 14, 2023
Figure 1 for Bounding Training Data Reconstruction in DP-SGD
Figure 2 for Bounding Training Data Reconstruction in DP-SGD
Figure 3 for Bounding Training Data Reconstruction in DP-SGD
Figure 4 for Bounding Training Data Reconstruction in DP-SGD
Viaarxiv icon

Extracting Training Data from Diffusion Models

Add code
Jan 30, 2023
Figure 1 for Extracting Training Data from Diffusion Models
Figure 2 for Extracting Training Data from Diffusion Models
Figure 3 for Extracting Training Data from Diffusion Models
Figure 4 for Extracting Training Data from Diffusion Models
Viaarxiv icon

Unlocking High-Accuracy Differentially Private Image Classification through Scale

Add code
Apr 28, 2022
Figure 1 for Unlocking High-Accuracy Differentially Private Image Classification through Scale
Figure 2 for Unlocking High-Accuracy Differentially Private Image Classification through Scale
Figure 3 for Unlocking High-Accuracy Differentially Private Image Classification through Scale
Figure 4 for Unlocking High-Accuracy Differentially Private Image Classification through Scale
Viaarxiv icon