Federal Grant Award Summary

The National Science Foundation (NSF) Division of Computer and Network Systems awarded a five-year CAREER Project Grant of $374,180 to the University of Texas at Dallas, effective October 1, 2026 through September 30, 2031, under the Computer and Information Science and Engineering program (CFDA 47.070). The award supports research to develop artificial intelligence (AI)-based methods for detecting software vulnerabilities in open-source software commits earlier in the development lifecycle. The project addresses security risks inherent in open-source software through three integrated research thrusts: refining input data by decomposing tangled commits and constructing fine-grained vulnerability datasets; developing multimodal AI representations that capture code-change semantics and commit behaviors including dependency evolution and repository development patterns; and creating an interpretable detection system designed to be practical for open-source communities with limited computational resources.

The project delivers interpretable and resource-efficient AI models capable of identifying risky code changes at the commit level rather than analyzing isolated code segments. Beyond the core research deliverables, the award supports broader impacts through education and workforce development in secure software engineering, positioning the work to enhance vulnerability detection practices across the open-source community while supporting critical infrastructure security in government, industry, and academia.