4 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…
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…
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…
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…