Melih Catal

I completed my undergraduate education at Sabancı University in Turkey and my master's degree at the University of Zurich. I started my doctoral studies at the University of Zurich in September 2024 under the supervision of Prof. Harald Gall. My research interests are software engineering, software security, machine learning, and cybersecurity.

I am happy to offer Bachelor’s and Master’s theses, as well as Master’s projects, on topics related to Trustworthy AI in Code LLMs. Several possible directions include:

• Fairness and bias evaluation in code generation
• Machine unlearning techniques in Code LLMs
• Memorization and data leakage issues in Code LLMs
• Explainability and interpretability of code generation
• Alternative optimization objectives for Code LLMs (e.g., training on abstract syntax tree (AST) structures instead of just next-token prediction)