---
res:
  bibo_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.@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Peter
      foaf_name: Súkeník, Peter
      foaf_surname: Súkeník
      foaf_workInfoHomepage: http://www.librecat.org/personId=d64d6a8d-eb8e-11eb-b029-96fd216dec3c
  - foaf_Person:
      foaf_givenName: Aleksei
      foaf_name: Kuvshinov, Aleksei
      foaf_surname: Kuvshinov
  - foaf_Person:
      foaf_givenName: Stephan
      foaf_name: Günnemann, Stephan
      foaf_surname: Günnemann
  bibo_volume: 162
  dct_date: 2022^xs_gYear
  dct_language: eng
  dct_publisher: ML Research Press@
  dct_title: Intriguing properties of input-dependent randomized smoothing@
...