Picture for Mathias Lécuyer

Mathias Lécuyer

Adaptive Randomized Smoothing: Certifying Multi-Step Defences against Adversarial Examples

Jun 14, 2024
Viaarxiv icon

Efficient and Adaptive Posterior Sampling Algorithms for Bandits

May 02, 2024
Viaarxiv icon

PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining

Feb 12, 2024
Viaarxiv icon

DP-AdamBC: Your DP-Adam Is Actually DP-SGD (Unless You Apply Bias Correction)

Add code
Dec 21, 2023
Viaarxiv icon

DP-Adam: Correcting DP Bias in Adam's Second Moment Estimation

Apr 21, 2023
Figure 1 for DP-Adam: Correcting DP Bias in Adam's Second Moment Estimation
Figure 2 for DP-Adam: Correcting DP Bias in Adam's Second Moment Estimation
Figure 3 for DP-Adam: Correcting DP Bias in Adam's Second Moment Estimation
Figure 4 for DP-Adam: Correcting DP Bias in Adam's Second Moment Estimation
Viaarxiv icon

Packing Privacy Budget Efficiently

Dec 26, 2022
Figure 1 for Packing Privacy Budget Efficiently
Figure 2 for Packing Privacy Budget Efficiently
Figure 3 for Packing Privacy Budget Efficiently
Figure 4 for Packing Privacy Budget Efficiently
Viaarxiv icon

GlueFL: Reconciling Client Sampling and Model Masking for Bandwidth Efficient Federated Learning

Dec 03, 2022
Figure 1 for GlueFL: Reconciling Client Sampling and Model Masking for Bandwidth Efficient Federated Learning
Figure 2 for GlueFL: Reconciling Client Sampling and Model Masking for Bandwidth Efficient Federated Learning
Figure 3 for GlueFL: Reconciling Client Sampling and Model Masking for Bandwidth Efficient Federated Learning
Figure 4 for GlueFL: Reconciling Client Sampling and Model Masking for Bandwidth Efficient Federated Learning
Viaarxiv icon

Sayer: Using Implicit Feedback to Optimize System Policies

Oct 28, 2021
Figure 1 for Sayer: Using Implicit Feedback to Optimize System Policies
Figure 2 for Sayer: Using Implicit Feedback to Optimize System Policies
Figure 3 for Sayer: Using Implicit Feedback to Optimize System Policies
Figure 4 for Sayer: Using Implicit Feedback to Optimize System Policies
Viaarxiv icon

Privacy Budget Scheduling

Add code
Jun 29, 2021
Figure 1 for Privacy Budget Scheduling
Figure 2 for Privacy Budget Scheduling
Figure 3 for Privacy Budget Scheduling
Figure 4 for Privacy Budget Scheduling
Viaarxiv icon

Practical Privacy Filters and Odometers with Rényi Differential Privacy and Applications to Differentially Private Deep Learning

Add code
Mar 02, 2021
Figure 1 for Practical Privacy Filters and Odometers with Rényi Differential Privacy and Applications to Differentially Private Deep Learning
Figure 2 for Practical Privacy Filters and Odometers with Rényi Differential Privacy and Applications to Differentially Private Deep Learning
Viaarxiv icon