• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Randomized Smoothing (almost) in Real Time?
 
  • Details
  • Full
Options
2023
Poster
Title

Randomized Smoothing (almost) in Real Time?

Title Supplement
Poster presented at the 40th International Conference on Machine Learning, 23-29 July 2023, Honolulu, Hawaii
Abstract
Certifying the robustness of Deep Neural Networks (DNNs) is very important in safety-critical domains. Randomized Smoothing (RS) has been recently proposed as a scalable, model-agnostic method for robustness verification, which has achieved excellent results and has been extended for a large variety of adversarial perturbation scenarios. However, a hidden cost in RS is during interference, since it requires passing tens-of-thousands perturbed samples through the DNN in order to perform the verification. In this work, we try to address this challenge, and explore what it would take to perform RS much faster, perhaps even in real-time, and what happens as we decrease the number of samples by orders of magnitude. Surprisingly, we find that the performance reduction in terms of average certified radius is not too large, even if we decrease the number of samples by two orders of magnitude, or more. This could possibly pave the way even for realtime robustness certification, under suitable settings. We perform a detailed analysis, both theoretically and experimentally, and show promising results on the standard CIFAR-10 and ImageNet datasets.
Author(s)
Seferis, Emmanouil
Fraunhofer-Institut für Kognitive Systeme IKS  
Kollias, Stefanos
National Technical University of Athens  
Burton, Simon  
Fraunhofer-Institut für Kognitive Systeme IKS  
Project(s)
IKS-Ausbauprojekt  
Funder
Bayerisches Staatsministerium für Wirtschaft, Landesentwicklung und Energie  
Conference
International Conference on Machine Learning 2023  
DOI
10.24406/publica-1930
File(s)
Seferis_RandomizedSmoothingAlmostInRealTime_2307_ICML_Poster.pdf (1.44 MB)
Rights
Under Copyright
Language
English
Fraunhofer-Institut für Kognitive Systeme IKS  
Fraunhofer Group
Fraunhofer-Verbund IUK-Technologie  
Keyword(s)
  • deep neural networks

  • DNN

  • robustness

  • robustness verification

  • randomized smoothing

  • RS

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024