M Lécuyer

Latest

• DPack: Efficiency-Oriented Privacy Budget Scheduling
• Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
• Panoramia: Privacy auditing of machine learning models without retraining
• Cookie Monster: Efficient On-device Budgeting for Differentially-Private Ad-Measurement Systems
• NetShaper: A Differentially Private Network Side-Channel Mitigation System
• Turbo: Effective Caching in Differentially-Private Databases
• Turbo: Effective Caching in Differentially-Private Databases
• Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments
• DP-Adam: Correcting DP Bias in Adam's Second Moment Estimation