← Search

Frederick Shpilevskiy

2 accepted papers

2024

Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences

NeurIPS 2024spotlight

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 smoothing using $f$-Differential Privacy to certify the adaptive composition of multiple steps. For the first time, our theo…

2024

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

AAAI 2024technical

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 traditional use of Differential Privacy (DP) with the Adam optimizer leads to sub-optimal performance on several tasks. We find th…