Intriguing Properties of Input-Dependent Randomized Smoothing

Peter Súkeník, Aleksei Kuvshinov, Stephan Günnemann

Research output: Contribution to journalConference articlepeer-review

1 Scopus citations

Abstract

Randomized smoothing is currently considered the state-of-the-art method to obtain certifiably robust classifiers. Despite its remarkable performance, the method is associated with various serious problems such as “certified accuracy waterfalls”, certification vs. accuracy trade-off, or even fairness issues. Input-dependent smoothing approaches have been proposed with intention of overcoming these flaws. However, we demonstrate that these methods lack formal guarantees and so the resulting certificates are not justified. We show that in general, the input-dependent smoothing suffers from the curse of dimensionality, forcing the variance function to have low semi-elasticity. On the other hand, we provide a theoretical and practical framework that enables the usage of input-dependent smoothing even in the presence of the curse of dimensionality, under strict restrictions. We present one concrete design of the smoothing variance function and test it on CIFAR10 and MNIST. Our design mitigates some of the problems of classical smoothing and is formally underlined, yet further improvement of the design is still necessary.

Original languageEnglish
Pages (from-to)20697-20743
Number of pages47
JournalProceedings of Machine Learning Research
Volume162
StatePublished - 2022
Event39th International Conference on Machine Learning, ICML 2022 - Baltimore, United States
Duration: 17 Jul 202223 Jul 2022

Fingerprint

Dive into the research topics of 'Intriguing Properties of Input-Dependent Randomized Smoothing'. Together they form a unique fingerprint.

Cite this