• 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. Logically Sound Arguments for the Effectiveness of ML Safety Measures
 
  • Details
  • Full
Options
2022
Conference Paper
Title

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  
Mainwork
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  
Conference
International Conference on Computer Safety, Reliability and Security 2022  
International Workshop on Artificial Intelligence Safety Engineering 2022  
DOI
10.1007/978-3-031-14862-0_25
Language
English
Fraunhofer-Institut für Kognitive Systeme IKS  
Keyword(s)
  • safety

  • machine learning

  • ML

  • pedestrian localization

  • post-processor

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