TraceVis: towards visualization for deep statistical model checking

Abstract

With the proliferation of neural networks (NN), the need to analyze, and ideally verify, their behavior becomes more and more pressing. Significant progress has been made in the analysis of individual NN decision episodes, but the verification of NNs as part of larger systems remains a grand challenge. Deep statistical model checking (DSMC) is a recent approach addressing that challenge in the context of Markov decision processes (MDP) where a NN represents a policy taking action decisions. The NN determinizes the MDP, resulting in a Markov chain which is analyzed by statistical model checking. Initial results in a Racetrack case study (a simple abstract encoding of driving control) suggest that such a DSMC analysis can be useful for quality assurance in system approval or certification. Here we explore the use of visualization to support DSMC users (human analysts, domain engineers). We …

@inproceedings{grosTraceVisTowardsVisualizationFor2021,
 author = {Timo P. Gros and David Groß and Stefan Gumhold and Jörg Hoffmann and Michaela Klauck and Marcel Steinmetz},
 booktitle = {Leveraging Applications of Formal Methods, Verification and Validation: Tools and Trends: 9th International Symposium on Leveraging Applications of Formal Methods, ISoLA 2020. International Symposium On Leveraging Applications of Formal Methods, Verification and Validation (ISoLA-2020), 9th International Symposium on Leveraging Applications of Formal Method, October 20-30, Rhodes, Greece},
 organization = {Springer International Publishing},
 pages = {27-46},
 publisher = {Springer International Publishing},
 title = {TraceVis: towards visualization for deep statistical model checking},
 volume = {Part IV 9},
 year = {2021}
}