Publications

A selection of recent work. See my Google Scholar profile for a complete list.

2025
Arguing Reliability of Machine Learning-based Components
B. C. Hu, L. Marsso, A. Di Sandro, M. Chechik
Engineering Reliable Autonomous Systems (EARS’25), 2025
Paper
Debugging and Runtime Analysis of Neural Networks with VLMs (A Case Study)

*Distinguised Paper Award Candidate

B. C. Hu, D. Gopinath, R. Mangal, N. Narodytska, C. Pasareanu, S. Jha
International Conference on AI Engineering – Software Engineering for AI (CAIN’25), 2025
Paper
Assessing Visually-Continuous Corruption Robustness of Neural Networks Relative to Human Performance
H. Shen, B. C. Hu, K. Czarnecki, L. Marsso, M. Chechik
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV’25), 2025
Paper Code
2024
Concept-based Analysis of Neural Networks via Vision-Language Models
R. Mangal, N. Narodytska, D. Gopinath, B. C. Hu, A. Roy, S. Jha, C. Pasareanu
International Symposium on AI Verifi cation (SAIV’24), 2024
Paper
2023
Towards Feature-Based Analysis of the Machine Learning Development Lifecycle
B. C. Hu, M. Chechik
Proceedings of the Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE’23), 2023
Paper
DecompoVision: Reliability Analysis of Machine Vision Components Through Decomposition and Reuse
B. C. Hu, L. Marsso, N.Dvornik, H. Shen, M. Chechik
Proceedings of the Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE’23), 2023
Paper Code
2022
What to Check: Systematic Selection of Transformations for Analyzing Reliability of Machine Vision Components
B. C. Hu, L. Marsso, K. Czarnecki, M. Chechik
International Symposium on Software Reliability Engineering(ISSRE’22), 2022
Paper
If a Human Can See It, So Should Your System: Reliability Requirements for Machine Vision Components
B. C. Hu, L. Marsso, K. Czarnecki, R. Salay, H. Shen, M. Chechik
International Conference on Software Engineering (ICSE’22), 2022
Paper Code