Saiyue Lyu

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

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…