• English
  • Deutsch
  • Log In
    Password Login
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Logically Sound Arguments for the Effectiveness of ML Safety Measures
 
  • Details
  • Full
Options
07 September 2022
Conference Paper
Titel

Logically Sound Arguments for the Effectiveness of ML Safety Measures

Abstract
We investigate the issues of achieving sufficient rigor in the arguments for the safety of machine learning functions. By considering the known weaknesses of DNN-based 2D bounding box detection algorithms, we sharpen the metric of imprecise pedestrian localization by associating it with the safety goal. The sharpening leads to introducing a conservative post-processor after the standard non-max-suppression as a counter-measure. We then propose a semi-formal assurance case for arguing the effectiveness of the post-processor, which is further translated into formal proof obligations for demonstrating the soundness of the arguments. Applying theorem proving not only discovers the need to introduce missing claims and mathematical concepts but also reveals the limitation of Dempster-Shafer’s rules used in semi-formal argumentation.
Author(s)
Cheng, Chih-Hong
Fraunhofer-Institut für Kognitive Systeme IKS
Schuster, Tobias
Fraunhofer-Institut für Kognitive Systeme IKS
Burton, Simon
Fraunhofer-Institut für Kognitive Systeme IKS
Hauptwerk
Computer Safety, Reliability, and Security. SAFECOMP 2022 Workshops, DECSoS, DepDevOps, SASSUR, SENSEI, USDAI, and WAISE. Proceedings
Project(s)
IKS-Ausbauprojekt
Funder
Bayerisches Staatsministerium für Wirtschaft, Landesentwicklung und Energie
Konferenz
International Conference on Computer Safety, Reliability and Security 2022
International Workshop on Artificial Intelligence Safety Engineering 2022
Thumbnail Image
DOI
10.1007/978-3-031-14862-0_25
Language
English
google-scholar
Fraunhofer-Institut für Kognitive Systeme IKS
Tags
  • safety

  • machine learning

  • ML

  • pedestrian localization

  • post-processor

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022