Sponsorship Award by the European Association for Computer Science Logic for the ESSLLI 2016 course "Model Counting for Logical Theories"
The 2011/2012 Best Paper Award of the DFG priority programme Reliably Secure Software Systems
Microsoft Research European Ph.D. scholarship 2008-2011
Dr. Rayna Dimitrova is tenure-track Faculty at CISPA. Before joining CISPA, she was a Lecturer (Assistant Professor) at the University of Sheffield, UK and at the University of Leicester, UK before that. Prior to that, Rayna held postdoctoral positions at the University of Texas at Austin, and at the Max Planck Institute for Software Systems in Germany. She received her PhD from Saarland University in Germany in 2014. Rayna’s research is in the area of formal methods, focusing on the specification, verification, and synthesis of reactive systems. She investigates primarily quantitative versions of these questions, centered around the aspect of uncertainty in system and environment models. She is particularly interested in applications of formal methods to autonomous systems, where her work addresses the limitations faced by autonomous control due to imperfect sensing and stochastic disturbances.
TACAS – International Conference on Tools and Algorithms for the Construction and Analysis of Systems29th International Conference on Tools and Algorithms for the Construction and Analysis of Systems
Robotics and Autonomous Systems
Logical Methods in Computer Science
Proceedings of the 21st Conference on Formal Methods in Computer-Aided Design – FMCAD 202121st Conference on Formal Methods in Computer-Aided Design – FMCAD 2021
Automated Technology for Verification and Analysis - 18th International Symposium, ATVA 2020, Hanoi, Vietnam, October 19-23, 2020, Proceedings18th International Symposium on Automated Technology for Verification and Analysis, ATVA 2020
Lecture Notes in Computer ScienceAutomated Technology for Verification and Analysis
Computer Aided Verification - 31th International Conference, CAV
Automated Technology for Verification and Analysis - 17th International Symposium, ATVA 2019, Taipei, Taiwan, October 28-31, 2019, Proceedings
28th International Conference on Concurrency Theory, CONCUR 2017, September 5-8, 2017, Berlin, Germany
Formal Methods for AI Safety
The rapid progress in artificial intelligence and machine learning has lead to the deployment of AI-based systems in a number of areas of modern life, such as manufacturing, transportation, and healthcare. However, serious concerns about the safety and trustworthiness of such systems still remain, due to the lack of assurance regarding their behavior. To address this problem, significant efforts in the area of formal methods in recent years have been dedicated to the development of rigorous techniques for the design of safe AI-based systems.
In this seminar, we will read and discuss research papers that present the latest results in this area. We will cover a range of topics, including the formal specification and verification of correctness properties of AI components of autonomous systems, and the design of reinforcement learning agents that respect safety constraints.
Each participant will give a presentation of an assigned paper, followed by a group discussion. All students are expected to read each paper carefully and to actively participate in the discussions.
Participation in all meetings is mandatory (exceptions require an official document, such as a doctor's certificate).
Each review is to be submitted before the meeting at which the paper will be presented and discussed.
In addition to your review you will have to submit 2 questions that you will ask to the presenter of the paper.
Each of the three reviews contributes 10% of your final grade.
The slides and presentation make up 40% of the final grade.
The summary will make up 30% of the final grade.