Yizheng Chen Receives NSF CAREER Award to Advance Secure Code Generation Research

University of Maryland computer science faculty member Yizheng Chen has received a National Science Foundation Faculty Early Career Development Program (CAREER) award to support research on improving the security of artificial intelligence tools used to write computer code.

Chen, an assistant professor in the Department of Computer Science with an appointment in the University of Maryland Institute for Advanced Computer Studies (UMIACS), is the principal investigator on the award, which is expected to total just under $573,000 over the next five years. The CAREER award is among the foundation’s most competitive funding programs for early-career faculty, supporting researchers who have the potential to serve as academic role models in both research and education and to advance the mission of their department or organization.

Her research focuses on Code Large Language Models (Code LLMs), AI systems that assist programmers by completing partial programs or generating code from natural language prompts. Used in tools such as ChatGPT, GitHub Copilot and Cursor, these models are increasingly integrated into development environments. While they can improve productivity, they may also generate code with vulnerabilities, creating security risks.

The project will design, develop and implement secure Code LLMs for realistic coding scenarios. Chen and her team will create benchmarks to measure the secure coding capabilities of these systems and explore techniques to improve their ability to detect and prevent vulnerabilities.

A 2023 GitHub survey found that 30% to 40% of respondents said their organizations promoted AI coding tool use, and Gartner projects that by 2028, 90% of enterprise software engineers will use such tools. Chen said these trends make security improvements essential for ensuring the reliability of critical software.

“This research will help improve the security of AI coding assistants, which could benefit millions of developers and many organizations,” Chen said.

She also envisions future Code LLMs that can analyze vulnerabilities and write secure programs, similar to the work of human security experts.

Chen conducts her research within the Maryland Cybersecurity Center (MC2) and UMIACS, focusing on the intersection of AI and security. She earned her Ph.D. in computer science from the Georgia Institute of Technology and completed postdoctoral work at the University of California, Berkeley and Columbia University.

Her previous work has received recognition, including an ACM Conference on Computer and Communications Security Best Paper Award Runner-up, a Google ASPIRE Award and selection as a Top 10 finalist in the CSAW Applied Research Competition. She is also a recipient of the Anita Borg Memorial Scholarship.

Chen said she values the NSF’s support for the project. 

“I am deeply grateful for the support from the National Science Foundation,” she said. “I am excited to begin this research and to work with graduate students to advance our goals.”

—Story by Samuel Malede Zewdu, CS Communications