Safety-critical systems should have their safety properties authoritatively established before they are considered for deployment. If this safety validation is performed via "black-box" methods (e.g., ones based on Deep Learning and related techniques) that are difficult for humans to comprehend, then an accompanying explanation should be provided as to why one may trust that the claim that safety has been validated. But what constitutes an acceptable explanation, and how do we verify the veracity of such explanations? -- these issues will be investigated in this presentation, with a particular focus on the explainability of safety properties relating to timing correctness (i.e., schedulability).

Dr. Sanjoy Baruah is Ina Champ Urbauer Professor at the department of Computer Science and Engineering, Washington University in St. Louis, St. Louis, MO, USA
Dr. Sanjoy Baruah (Fellow, IEEE) was with the University of North Carolina at Chapel Hill, Chapel Hill, NC, USA, from 1999 to 2017, and The University of Vermont, Burlington, VT, USA, from 1993 to 1999. He joined the Washington University in St. Louis, St. Louis, MO, USA, in September 2017. His research interests and activities are in real-time and safety-critical system design, scheduling theory, resource allocation and sharing in distributed computing environments, and algorithm design and analysis. He is a Fellow of the IEEE, and the recipient of the 2014 Outstanding Technical Contributions and Leadership Award of the IEEE Technical Committee on Real-Time Systems.