Successfully Defended MS Thesis at KAIST

I am excited to announce that I have successfully defended my Master’s thesis titled “Systematic Dataset Construction for Deep Learning-Based Fault Localization(DLFL) with Mutation-Based Fault Localization(MBFL) Features” at KAIST. This marks the completion of my Master’s degree in Computer Science, and I am grateful for the support and guidance from my advisor, Prof. Moonzoo Kim, and my colleagues at the Software Testing and Verification Group (SWTV Lab).

During my research, I focused on enhancing fault localization techniques using deep learning and mutation-based methods, with a particular emphasis on applying these techniques to real-world industrial software systems. My work involved practical applications in military defense software and industry software testing tools, demonstrating the effectiveness of these advanced fault localization approaches in critical production environments. I believe that the findings from my thesis will contribute to the advancement of software testing and verification, particularly in industrial and safety-critical domains, and I look forward to exploring new opportunities in this field.