Intrinsic Robustness

Built upon on a novel definition of label uncertainty, we develop an empirical method to estimate a more realistic intirnsic robustness limit for image classification tasks.

Advocate to understand the concentration of measure phenomenon regarding inputs regions with high label uncertainty

We show that concentration of measure does not prohibit the existence of adversarially robust classifiers using a novel method of empirical concentration estimation.

We propose a way to characterize the intrinsic robustness of image distributions under L2 perturbations using conditional generative models.

We develop a method to measure the concentration of image benchmarks using empirical samples and show that concentration of measure does not prohibit the existence of adversarially robust classifiers.