Purdue CS team earns recognition in Amazon Nova AI Challenge
08-20-2025
Purdue’s Amazon Nova AI team, PurCL.
A team of Purdue University computer science researchers earned international recognition in the Amazon Nova AI Challenge, advancing the development of safer and more trustworthy AI coding assistants.
The Purdue team, PurCL, competed as a “red team,” tasked with uncovering vulnerabilities in AI systems designed to help developers write code securely. Their work combined expertise in AI security, program analysis and software security to create advanced testing tools that exposed weaknesses in AI coding models.
Team leaders were Xiangzhe Xu and Guangyu Shen, both Ph.D. students in the Department of Computer Science. Xu focused on program analysis and software security, while Shen concentrated on AI safety and model analysis.
Two specialized subgroups drove the project. The in-house red team, led by Siyuan Cheng, developed and reproduced more than 17 advanced red-teaming techniques to probe AI defenses. The in-house blue team, led by Zian Su, created simulated defense systems to rigorously evaluate the red team’s strategies.
Other Ph.D. students contributing to the project included Hanxi Guo, Lu Yan, Xuan Chen, Jiasheng Jiang and Xiaolong Jin, each lending expertise to either offensive or defensive strategies.
The team was advised by Xiangyu Zhang, Samuel Conte Professor of Computer Science; Chengpeng Wang, postdoctoral research associate; and Zhuo Zhang, formerly a Purdue postdoctoral research associate and now an assistant professor at Columbia University.
“Our approach was like crash testing for AI coding assistants,” Shen said. “Just as cars are tested in real-world accident scenarios, we developed tools that stress-test AI models in realistic coding environments to reveal hidden flaws. The ultimate goal is to make these systems both secure and reliable for developers.”
Purdue’s participation was supported by Amazon through the Nova Challenge.
This work contributes to Purdue’s growing leadership in trustworthy AI research, building tools that can help industry deploy safer AI systems across fields like finance, health care and cybersecurity.
About the Department of Computer Science at Purdue University
Founded in 1962, the Department of Computer Science was created to be an innovative base of knowledge in the emerging field of computing as the first degree-awarding program in the United States. The department continues to advance the computer science industry through research. U.S. News & World Report ranks the department No. 8 in computer engineering and No. 16 overall in undergraduate and graduate computer science. Additionally, the program is ranked No. 6 in cybersecurity, No. 8 in software engineering, No. 13 in systems, No. 15 in programming languages and data analytics, and No. 18 in theory. Graduates of the program are able to solve complex and challenging problems in many fields. Our consistent success in an ever-changing landscape is reflected in the record undergraduate enrollment, increased faculty hiring, innovative research projects, and the creation of new academic programs. The increasing centrality of computer science in society, academic disciplines and new research activities — centered around foundations and applications of artificial intelligence and machine learning, such as natural language processing, human computer interaction, vision, and robotics, as well as systems and security — are the future focus of the department. Learn more at cs.purdue.edu.