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.
This work is funded by the Bavarian Ministry for Economic Affairs, Regional Development and Energy as part of a project to support the thematic development of the Fraunhofer Institute for Cognitive Systems.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Due to space limits, we refer readers to the extended version [2] for details including the formal proof.
References
ISO/PAS 21448:2019 road vehicles - safety of the intended functionality (2019). https://www.iso.org/standard/70939.html
Cheng, C.-H., Schuster, T., Burton, S.: Logically sound arguments for the effectiveness of ml safety measures. arXiv preprint arXiv:2111.02649 (2021)
Cyra, L., Gorski, J.: Support for argument structures review and assessment. Reliab. Eng. Syst. Saf. 96(1), 26–37 (2011)
Dai, X., et al.: Dynamic head: unifying object detection heads with attentions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7373–7382. IEEE (2021)
Idmessaoud, Y., Dubois, D., Guiochet, J.: Belief functions for safety arguments confidence estimation: a comparative study. In: Davis, J., Tabia, K. (eds.) SUM 2020. LNCS (LNAI), vol. 12322, pp. 141–155. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58449-8_10
Kelly, T., Weaver, R.: The goal structuring notation - a safety argument notation. In: Proceedings of the Dependable Systems and Networks Workshop on Assurance Cases, p. 6. Citeseer (2004)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Owre, S., Rushby, J.M., Shankar, N.: PVS: a prototype verification system. In: Kapur, D. (ed.) CADE 1992. LNCS, vol. 607, pp. 748–752. Springer, Heidelberg (1992). https://doi.org/10.1007/3-540-55602-8_217
Sentz, K., Ferson, S.: Combination of evidence in Dempster-Shafer theory, vol. 4015. Sandia National Laboratories (2002)
Wang, R.: Confidence in safety argument-an assessment framework based on belief function theory. Ph.D. thesis, INSA de Toulouse (2018)
Yuan, C., Wu, J., Liu, C., Yang, H.: A subjective logic-based approach for assessing confidence in assurance case. Int. J. Performability Eng. 13(6), 807 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Cheng, CH., Schuster, T., Burton, S. (2022). Logically Sound Arguments for the Effectiveness of ML Safety Measures. In: Trapp, M., Schoitsch, E., Guiochet, J., Bitsch, F. (eds) Computer Safety, Reliability, and Security. SAFECOMP 2022 Workshops . SAFECOMP 2022. Lecture Notes in Computer Science, vol 13415. Springer, Cham. https://doi.org/10.1007/978-3-031-14862-0_25
Download citation
DOI: https://doi.org/10.1007/978-3-031-14862-0_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-14861-3
Online ISBN: 978-3-031-14862-0
eBook Packages: Computer ScienceComputer Science (R0)