Students Advance in Amazon Challenge
A University of Texas at Dallas student team is one of 10 from around the world selected to compete in a new Amazon tournament designed to strengthen the security of software developed with the assistance of artificial intelligence.
The Comets are competing in the Amazon Nova AI Challenge as one of five red teams that must find vulnerabilities and flaws in code-generating models developed by five model developer teams. The teams were selected from over 90 proposals.
The tournament kicked off in January, and the final round will be held in June. Each team received $250,000 in sponsorship, monthly Amazon Web Services credits and the chance to compete for top prizes. The winning red team and model developer team will receive $250,000 each. Second-place teams will receive $100,000.
The UTD team, called ASTRO (AI Security and Trustworthiness Operations), is led by Zexin (Jason) Xu, a computer science PhD student who served as an engineering lead in the first Amazon Alexa Prize SimBot Challenge as a master’s student at Ohio State University.
Xu said the work “has been like learning to fly while building the rocket.”
“There’s something exhilarating about being professional AI ‘hackers,’ with ethical boundaries, searching for vulnerabilities in the vast universe of large language models so they can be patched before they can cause any harm,” Xu said. “There’s a certain cosmic poetry to our work — just as our university’s Comet mascot streaks across the sky, we’re charting new trajectories in AI safety.”
Other team members include computer science doctoral students Ravishka Rathnasuriya, Tingxi Li and Zihe Song; Jun Ren BS’24; computer science senior Bhavesh Mandalapu; and mechanical engineering doctoral student Soroush Setayeshpour.
“What makes ASTRO particularly unique is our team’s diverse composition and depth of expertise across all academic levels,” said Dr. Wei Yang, associate professor of computer science in the Erik Jonsson School of Engineering and Computer Science and one of the team’s faculty advisors. Dr. Xinya Du, assistant professor of computer science, also serves as an advisor to the team.
A version of this story appeared in News Center.