Dimitrios Boursinos
Papers
2
Total Citations
17
H-Index
2
About
Dimitrios Boursinos is a researcher specializing in the safety and trustworthiness of learning-enabled cyber-physical systems (CPS), with a particular focus on assurance monitoring and uncertainty quantification for machine learning components. His work addresses a critical challenge in modern engineering: as deep neural networks become increasingly embedded in CPS applications, they introduce novel hazard profiles that traditional safety frameworks struggle to capture. Boursinos has made notable contributions by developing assurance monitoring frameworks that leverage inductive conformal prediction and distance learning techniques to detect when machine learning components operate outside their reliable boundaries. His 2021 paper on conformal prediction-based monitoring has garnered 9 citations, while his foundational 2020 work on assurance monitoring of CPS with machine learning components has accumulated 8 citations — together representing a growing body of influence in a field where safety-critical reliability is paramount. His research bridges the gap between machine learning practice and systems engineering rigor, offering practical tools for building trustworthy AI-integrated systems in domains where failures can have serious real-world consequences. Students and practitioners working at the intersection of AI safety, autonomous systems, and dependable computing will find his contributions particularly relevant.
Research Focus
Key Achievements
Top Papers
- 1
- 2