---
_id: '12664'
abstract:
- lang: eng
  text: 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.
article_processing_charge: No
arxiv: 1
author:
- first_name: Peter
  full_name: Súkeník, Peter
  id: d64d6a8d-eb8e-11eb-b029-96fd216dec3c
  last_name: Súkeník
- first_name: Aleksei
  full_name: Kuvshinov, Aleksei
  last_name: Kuvshinov
- first_name: Stephan
  full_name: Günnemann, Stephan
  last_name: Günnemann
citation:
  ama: 'Súkeník P, Kuvshinov A, Günnemann S. Intriguing properties of input-dependent
    randomized smoothing. In: <i>Proceedings of the 39th International Conference
    on Machine Learning</i>. Vol 162. ML Research Press; 2022:20697-20743.'
  apa: 'Súkeník, P., Kuvshinov, A., &#38; Günnemann, S. (2022). Intriguing properties
    of input-dependent randomized smoothing. In <i>Proceedings of the 39th International
    Conference on Machine Learning</i> (Vol. 162, pp. 20697–20743). Baltimore, MD,
    United States: ML Research Press.'
  chicago: Súkeník, Peter, Aleksei Kuvshinov, and Stephan Günnemann. “Intriguing Properties
    of Input-Dependent Randomized Smoothing.” In <i>Proceedings of the 39th International
    Conference on Machine Learning</i>, 162:20697–743. ML Research Press, 2022.
  ieee: P. Súkeník, A. Kuvshinov, and S. Günnemann, “Intriguing properties of input-dependent
    randomized smoothing,” in <i>Proceedings of the 39th International Conference
    on Machine Learning</i>, Baltimore, MD, United States, 2022, vol. 162, pp. 20697–20743.
  ista: 'Súkeník P, Kuvshinov A, Günnemann S. 2022. Intriguing properties of input-dependent
    randomized smoothing. Proceedings of the 39th International Conference on Machine
    Learning. ICML: International Conference on Machine Learning vol. 162, 20697–20743.'
  mla: Súkeník, Peter, et al. “Intriguing Properties of Input-Dependent Randomized
    Smoothing.” <i>Proceedings of the 39th International Conference on Machine Learning</i>,
    vol. 162, ML Research Press, 2022, pp. 20697–743.
  short: P. Súkeník, A. Kuvshinov, S. Günnemann, in:, Proceedings of the 39th International
    Conference on Machine Learning, ML Research Press, 2022, pp. 20697–20743.
conference:
  end_date: 2022-07-23
  location: Baltimore, MD, United States
  name: 'ICML: International Conference on Machine Learning'
  start_date: 2022-07-17
corr_author: '1'
date_created: 2023-02-20T08:30:21Z
date_published: 2022-07-19T00:00:00Z
date_updated: 2025-07-10T11:50:28Z
day: '19'
ddc:
- '004'
external_id:
  arxiv:
  - '2110.05365'
file:
- access_level: open_access
  checksum: ab8695b1e24fb4fef4f1f9cd63ca8238
  content_type: application/pdf
  creator: chl
  date_created: 2023-02-20T08:30:10Z
  date_updated: 2023-02-20T08:30:10Z
  file_id: '12665'
  file_name: sukeni-k22a.pdf
  file_size: 8470811
  relation: main_file
  success: 1
file_date_updated: 2023-02-20T08:30:10Z
has_accepted_license: '1'
intvolume: '       162'
language:
- iso: eng
month: '07'
oa: 1
oa_version: Published Version
page: 20697-20743
publication: Proceedings of the 39th International Conference on Machine Learning
publication_status: published
publisher: ML Research Press
quality_controlled: '1'
scopus_import: '1'
status: public
title: Intriguing properties of input-dependent randomized smoothing
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 162
year: '2022'
...