Xinyu Xing (Northwestern)- Toward Autonomous Cybersecurity Systems: Scaling Security Expertise with AI
Abstract: Cybersecurity faces a fundamental scalability crisis: while software systems grow exponentially in complexity, the supply of human expertise does not. This talk presents a vision for autonomous cybersecurity systems — AI agents that can perform the work of expert analysts at scale. I will highlight why today’s approaches fall short and outline three core barriers to this vision. Building on this foundation, I will introduce a series of systems that address these challenges.
Speakers
Xinyu Xing
Xinyu Xing is an Associate Professor of Computer Science at Northwestern University and co-founder of Sec3 and B3YOND. His research lies at the intersection of cybersecurity and artificial intelligence, with a focus on software, systems, and AI security.
His work aims to develop new techniques for analyzing, securing, and improving the robustness of complex software systems, as well as leveraging AI to enhance cybersecurity analysis and automation.
Professor Xing received his Ph.D. in Computer Science from the Georgia Institute of Technology. He has made significant contributions to areas such as vulnerability analysis, kernel security, reverse engineering, and AI security, and has published extensively in top-tier venues including USENIX Security, ACM CCS, and NeurIPS.
His research has received numerous recognitions, including the NSF CAREER Award, Amazon Research Awards, and multiple best paper awards at leading security conferences. His work has also been featured in major media outlets such as MIT Technology Review and The New York Times.
In addition, he has been actively involved in advancing AI-driven cybersecurity through competitive research efforts. He led team 42-b3yond-6ug in the DARPA AI Cyber Challenge (AIxCC), where the team advanced to the final round, demonstrating cutting-edge progress toward autonomous vulnerability detection and mitigation.
Beyond academia, he actively engages with the security community through industry collaborations and participation in venues such as Black Hat and DEF CON, and his research has been deployed in real-world systems.
