Search Results for author:
Found 8 papers, 3 papers with code
PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
We introduce a privacy auditing scheme for ML models that relies on membership inference attacks using generated data as "non-members".
DP-AdamBC: Your DP-Adam Is Actually DP-SGD (Unless You Apply Bias Correction)
The Adam optimizer is a popular choice in contemporary deep learning, due to its strong empirical performance.
DP-Adam: Correcting DP Bias in Adam's Second Moment Estimation
We observe that the traditional use of DP with the Adam optimizer introduces a bias in the second moment estimation, due to the addition of independent noise in the gradient computation.
Packing Privacy Budget Efficiently
This DP budget can be regarded as a new type of compute resource in workloads of multiple ML models training on user data.
GlueFL: Reconciling Client Sampling and Model Masking for Bandwidth Efficient Federated Learning
Federated learning (FL) is an effective technique to directly involve edge devices in machine learning training while preserving client privacy.
Sayer: Using Implicit Feedback to Optimize System Policies
We develop a methodology, called Sayer, that leverages implicit feedback to evaluate and train new system policies.
Privacy Budget Scheduling
We describe PrivateKube, an extension to the popular Kubernetes datacenter orchestrator that adds privacy as a new type of resource to be managed alongside other traditional compute resources, such as CPU, GPU, and memory.
Practical Privacy Filters and Odometers with Rényi Differential Privacy and Applications to Differentially Private Deep Learning
Differential Privacy (DP) is the leading approach to privacy preserving deep learning.
