Date & Time:
March 31, 2025 2:00 pm – 3:00 pm
Location:
Crerar 298, 5730 S. Ellis Ave., Chicago, IL,
03/31/2025 02:00 PM 03/31/2025 03:00 PM America/Chicago Yevgeniy Vorobeychik (Washington University)- Achieving AI Safety in a Contested World Crerar 298, 5730 S. Ellis Ave., Chicago, IL,

Abstract: As the increasing capabilities of AI-enabled systems have led to broad deployment across diverse applications ranging from conversational agents to self-driving cars, safety considerations have come to be central to the current research agenda. However, the very meaning of safety has come to be broad and in some cases contested. For example, there may be responses to conversational prompts that some may deem neutral, while others offensive, or autonomous driving behaviors that some may view as efficient while others perceive them as dangerously aggressive. A useful way to conceptualize safety considerations is to divide these into two categories: objective and subjective. The former (for example, running over a pedestrian) is not reasonable contested, while the latter (for example, how aggressively a self-driving car should merge onto a freeway) can admit a range of legitimate perspectives.

In this talk, I will present our recent work tackling both objective and subjective safety considerations. On the former, I will present learning-based approaches for synthesizing provably stable and safe neural network controllers in known dynamical systems, combining gradient-based methods for both synthesis and verification with ideas from curriculum learning. Further, I will briefly discuss our recent work that facilitates safety specifications that combine natural language with formal logic, in which we combine LLMs with conformal prediction to obtain provably correct plans. For the latter, I will discuss an axiomatic framework for preference learning that accounts for disagreement in safety preferences, as well as a novel approach for reinforcement learning with diverse task (e.g., safety) specifications that achieves provable performance guarantees and state-of-the-art performance in zero-shot and few-shot settings.

Speakers

headshot

Yevgeniy Vorobeychik

Professor, Washington University

Yevgeniy Vorobeychik is a Professor of Computer Science & Engineering at Washington University in Saint Louis. Previously, he was an Assistant Professor of Computer Science at Vanderbilt University. Between 2008 and 2010 he was a post-doctoral research associate at the University of Pennsylvania Computer and Information Science department. He received Ph.D. (2008) and M.S.E. (2004) degrees in Computer Science and Engineering from the University of Michigan, and a B.S. degree in Computer Engineering from Northwestern University. His work focuses on game theoretic modeling of security and privacy, adversarial machine learning, algorithmic and behavioral game theory and incentive design, optimization, agent-based modeling, complex systems, network science, and epidemic control. Dr. Vorobeychik received an NSF CAREER award in 2017, and was invited to give an IJCAI-16 early career spotlight talk. He also received several Best Paper awards, including one of 2017 Best Papers in Health Informatics. He was nominated for the 2008 ACM Doctoral Dissertation Award and received honorable mention for the 2008 IFAAMAS Distinguished Dissertation Award.

Related News & Events

headshots
UChicago CS News

University of Chicago PhD Graduates Secure Tenure-Track Faculty Positions Amid a Competitive Job Market

Jun 25, 2025
text to 3d example
UChicago CS News

Democratizing Digital Graphics: An Undergrad’s Unlikely Path To Putting Agency of 3D-Generation in Users’ Hands

Jun 17, 2025
headshot
UChicago CS News

Faculty Spotlight: Get to Know Kexin Pei

Jun 03, 2025
David Cash
UChicago CS News

David Cash Receives 2025 Quantrell Award for Undergraduate Teaching

Jun 02, 2025
future of AI panelists
Video

The Future of AI Panel: Alumni Weekend

May 30, 2025
Steven Song and Spencer Ellis
UChicago CS News

Bridging Medicine and Machine Learning: Predicting Skin Cancer in Resource-Limited Settings

May 28, 2025
UChicago CS News

Hands-On Vision: How a Wrist Camera Can Expand the World for All Users

May 23, 2025
students accepting best paper award
UChicago CS News

UChicago Students Received ACM EuroSys Best Paper for CacheBlend, a Game-Changer in AI Speed and Precision

May 22, 2025
Video

Can we authenticate human creativity?

May 19, 2025
robot interaction
In the News

More Control, Less Connection: How User Control Affects Robot Social Agency

May 16, 2025
headshot
Video

AI and the Future of Work Panel: Featuring Nick Feamster

May 06, 2025
collage of photos from conference
UChicago CS News

Innovation at the Forefront: UChicago CS Researchers Make Significant Contributions to CHI 2025

Apr 23, 2025
arrow-down-largearrow-left-largearrow-right-large-greyarrow-right-large-yellowarrow-right-largearrow-right-smallbutton-arrowclosedocumentfacebookfacet-arrow-down-whitefacet-arrow-downPage 1CheckedCheckedicon-apple-t5backgroundLayer 1icon-google-t5icon-office365-t5icon-outlook-t5backgroundLayer 1icon-outlookcom-t5backgroundLayer 1icon-yahoo-t5backgroundLayer 1internal-yellowinternalintranetlinkedinlinkoutpauseplaypresentationsearch-bluesearchshareslider-arrow-nextslider-arrow-prevtwittervideoyoutube