Kevin Lira

I study how large language models can support secure software engineering, especially automated software vulnerability detection and repair. This research focuses on practical methods for reasoning about production codebases, interprocedural context, multiple programming languages, and the cost of applying modern LLMs in vulnerability analysis workflows.

• LLM-based vulnerability detection with interprocedural code context.
• Cross-language vulnerability repair and automated program repair.
• Secure development workflows for real-world software systems.
• Automated software testing with generative AI and browser automation.

Selected papers include work on LLM vulnerability detection across languages, cross-language vulnerability repair, and Gemini-generated Selenium tests. View the full publications page.

Find my research on Google Scholar and ORCID.