About
I am a research assistant and PhD candidate at the Institute for Software Systems at the Hamburg University of Technology (TUHH). I am an associate fellow at the CAUSE research group. Below, an overview of my research interests and publications is provided.
Research Interests
- Fault Localization Methods for Neural Networks
- Software Engineering Methods for Neural Networks
- Scalability and Efficiency of Software Engineering Methods for Neural Networks
- Adversarial Input Generation for Neural Networks
- LLM-Assisted Education and Automated Exercise Generation
Publications
Conference Papers
-
M. B. Hoffmann, D. Rashedi, and S. Schupp, “Automatically Generating Programming Exercises with Open-Source LLMs: Integrating Lecture Slides and Learning Objectives,” 15th International Workshop on Trends in Functional Programming in Education (TFPiE 2026), Odense, Denmark, Jan 2026.
-
D. Rashedi and S. Schupp, “Efficient Hit-Spectrum-Guided Fast Gradient Sign Method: An Adjustable Approach with Memory and Runtime Optimizations,” 20th International Conference on Software Technologies (ICSOFT 2025), Bilbao, Spain, Jun 2025. Nominated for Best Paper Award.
-
D. Rashedi and S. Schupp, “Neural Network Pruning Based on Spectrum-Based Fault Localization and Particle Swarm Optimization,” 4th IEEE International Conference on Software Engineering and Artificial Intelligence (SEAI 2024), Xiamen, China, Jun 2024.
Journal Articles
- D. Rashedi and S. Schupp, “Efficient Adversarial Generation through Selective SBFL Guidance and Automated Sub-Model Strategy,” Communications in Computer and Information Science (CCIS), 2025.