Are you an aspiring researcher passionate about software engineering with a strong interest in real-world industrial applications? Are you interested in ground-breaking research on security vulnerabilities and explainable AI that will help software engineers identify, fix and understand software bugs more efficiently? If so, you have a key role to play as a PhD candidate in the Find2Fix project! Software errors and vulnerabilities, or bugs, consume significant time and resources from software engineers. Several solutions have been implemented, from memory-safe programming languages to coding assistants designed to help developers write safer, more efficient and maintainable code. Despite this, developers continue to develop buggy code, often without fully understanding the root causes or how to effectively fix them.
In the
Find2Fix: Reducing Software Errors using Transparent AI project, we engineer the first open-source tool for the entire process from software error discovery to mitigation based on security testing and model inference (PhD1) and explainable AI (PhD2) technology. Your main responsibilities as a PhD candidate will be to conduct cutting-edge research within the Find2Fix project. Your research will be published and presented at international AI, software engineering and security venues.
The first position, supervised by Erik Poll and Harald Vranken, explores the combination of security testing, such as fuzzing or other techniques for static (SAST) and dynamic (DAST) analysis, with model inference using Sicco Verwer's FlexFringe tool. This tool maps execution traces to automata that model software behaviour, which can then be used to analyse security flaws.
The second position, supervised by Mairieli Wessel and Frits Vaandrager, focuses on explaining the root cause of already identified bugs and why a suggested fix works, tailoring explanations to the varying contexts and needs of software engineers. You will research and apply explainable AI techniques, engaging with software engineers via case studies, interviews and other empirical methods to better understand their perspectives, and refine and evaluate the quality of the explanations.
As a PhD candidate, you will be part of a dynamic and collaborative research group. The Find2Fix project is a joint initiative involving two industrial partners - ASML and dCodis (a startup). Alongside the rest of the team, you will contribute to developing demonstrators for the Find2Fix technology at our industrial partners. This project fosters a close collaboration between Radboud University and TU Delft, where two additional PhD students will also work on Find2Fix under the supervision of
Dr Sicco Verwer,
Dr Annibale Panichella, and
Dr Sebastijan Dumančić.
Your teaching load will be up to 10% of your working time.
Would you like to learn more about what it’s like to pursue a PhD at Radboud University? Visit the page about working as a PhD candidate.