School of Information Sciences

The AI Disruption Speaker Series: Chaowei Xiao

Chaowei Xiao

Chaowei Xiao will present "Towards Secure and Safe AI Agents: From Model to System." 

Chaowei Xiao is an Assistant Professor at Johns Hopkins University and a Researcher at NVIDIA. His research focuses on building next-generation secure and trustworthy AI and Agents.  He has received several prestigious honors, including the Schmidt Science AI2050 Early Career Award, Argonne National Lab Impact Award, and multiple industry faculty awards from Amazon and Apple. His work has won various awards including the USENIX Security Distinguished Paper Award (2024),MobiCom Best Paper Award (2014),  EWSN Best Paper Award (2021), ACM Gordon Bell Prize Finalist (2024) and Bell Special Prize (2023). His research has been cited around 20,000 times and featured in leading media outlets including Nature, Wired, Fortune, and The New York Times. He also holds multiple patents, and his research has been exhibited at the London Science Museum. Before joining JHU, he was an Assistant Professor at the University of Wisconsin–Madison.  His group at JHU has multiple PhD, postdoc and interns openings. Interested applicants are encouraged to contact him.

Abstract:
Immense efforts are underway to align AI with human values and ensure its responsible use. Yet a profound question remains: is AI truly safe? In this talk, I will share our the Dual Pathways Principle that unites the model and system perspectives to build secure and safe AI agents.  I will introduce our recent work, which integrates security and human-centric principles to build secure and safe AI. Then, I will discuss why ensuring AI safety demands a system-level approach and present our security-by-design approaches for building secure and safe AI agents.  Combining them together, I aim to lay out a pathway toward secure and safe AI agents. 

About the speaker series:
The CIRSS Speaker Series continues in Fall on the new theme of “The AI Disruption.” Our speakers will discuss how recent advances in AI have reshaped their research — what has been made easier and what has become more difficult — and reflect upon its broader disruptive impact on society.

We meet most Wednesdays, 9am-10am Central time, in Zoom. Everyone is welcome to attend. More information, including upcoming speaker schedule and links to recordings, is available on the series webpage. For weekly updates on upcoming talks, subscribe to our CIRSS Seminars mailing list. Our Fall series is led by Yuanxi Fu and Timothy McPhillips, and supported by the Center for Informatics Research in Science and Scholarship (CIRSS) and the School of Information Sciences at the University of Illinois Urbana-Champaign.  

This event is sponsored by Center for Informatics Research in Science and Scholarship

School of Information Sciences

501 E. Daniel St.

MC-493

Champaign, IL

61820-6211

Voice: (217) 333-3280

Fax: (217) 244-3302

Email: ischool@illinois.edu

Back to top