A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Certified Robustness via Locally Biased Randomized Smoothing
2022
Conference on Learning for Dynamics & Control
The successful incorporation of machine learning models into safety-critical control systems requires rigorous robustness guarantees. Randomized smoothing remains one of the state-of-the-art methods for robustification with theoretical guarantees. We show that using uniform and unbiased smoothing measures, as is standard in the literature, relies on the underlying assumption that smooth decision boundaries yield good robustness, which manifests into a robustness-accuracy tradeoff. We generalize
dblp:conf/l4dc/AndersonS22
fatcat:ehcyzhpkqnff7avxakjnum65zm