8 citations · 17 across the 9 of their papers we have counts for
9 papers
Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
Saiyue Lyu, Shadab Shaikh, Frederick Shpilevskiy +2
We propose Adaptive Randomized Smoothing (ARS) to certify the predictions of our test-time adaptive models against adversarial examples. ARS extends the analysis of randomized smoo…
Cookie Monster: Efficient On-device Budgeting for Differentially-Private Ad-Measurement Systems
Pierre Tholoniat, Kelly Kostopoulou, Peter McNeely +6
With the impending removal of third-party cookies from major browsers and the introduction of new privacy-preserving advertising APIs, the research community has a timely opportuni…
PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
Mishaal Kazmi, Hadrien Lautraite, Alireza Akbari +5
We present PANORAMIA, a privacy leakage measurement framework for machine learning models that relies on membership inference attacks using generated data as non-members. By relyin…
DP-AdamBC: Your DP-Adam Is Actually DP-SGD (Unless You Apply Bias Correction)
Qiaoyue Tang, Frederick Shpilevskiy, Mathias Lécuyer
The Adam optimizer is a popular choice in contemporary deep learning, due to its strong empirical performance. However we observe that in privacy sensitive scenarios, the tradition…
DP-Adam: Correcting DP Bias in Adam's Second Moment Estimation
Qiaoyue Tang, Mathias Lécuyer
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 comput…
GlueFL: Reconciling Client Sampling and Model Masking for Bandwidth Efficient Federated Learning
Shiqi He, Qifan Yan, Feijie Wu +3
Federated learning (FL) is an effective technique to directly involve edge devices in machine learning training while preserving client privacy. However, the substantial communicat…
DPack: Efficiency-Oriented Privacy Budget Scheduling
Pierre Tholoniat, Kelly Kostopoulou, Mosharaf Chowdhury +4
Machine learning (ML) models can leak information about users, and differential privacy (DP) provides a rigorous way to bound that leakage under a given budget. This DP budget can…
Privacy Budget Scheduling
Tao Luo, Mingen Pan, Pierre Tholoniat +3
Machine learning (ML) models trained on personal data have been shown to leak information about users. Differential privacy (DP) enables model training with a guaranteed bound on t…
Practical Privacy Filters and Odometers with Rényi Differential Privacy and Applications to Differentially Private Deep Learning
Mathias Lécuyer
Differential Privacy (DP) is the leading approach to privacy preserving deep learning. As such, there are multiple efforts to provide drop-in integration of DP into popular framewo…