Jonathan Gregory

Jonathan Gregory

Computer Science PhD Student
University of Wisconsin-Madison
jgregory8 at wisc dot edu

About Me

I am a PhD student in Computer Science at the University of Wisconsin-Madison, where I am advised by Prof. Patrick McDaniel in the Madison Security and Privacy Research Group. Prior to beginning my graduate studies, I received bachelor's degrees in Computer Science, Cybersecurity, and Mathematics from Central Michigan University.

My current research focuses on the security of multi-agent systems. My research interests also include:

  • Trustworthy artificial intelligence
  • Adversarial machine learning
  • Cybersecurity

I am grateful to be supported as a NSF GRFP fellow.


Updates


Selected Papers

  • The Limits of Information-Flow Control Enforcement for Agentic Systems
    Jonathan Gregory, Kyle Domico, Kunyang Li, Jean-Charles Noirot Ferrand, Patrick McDaniel
    Inaugural Workshop on Agentic AI in Offensive and Defensive Cyber Operations (AIDC'26), 2026
  • MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems
    Kunyang Li, Kyle Domico, Jonathan Gregory, Patrick McDaniel
    In submission, 2026
  • Activation-Free Backbones for Image Recognition: Polynomial Alternatives for Spatial and Channel Mixing
    Jeffrey Wang, Jonathan Gregory, Grigorios Chrysos
    International Conference on Machine Learning (ICML), 2026

Selected Awards

  • Graduate Research Fellowship (GRFP), U.S. National Science Foundation, 2026
  • Academic Excellence Award, Central Michigan University Honors Program, 2025
  • President's Award for Undergraduate Research and Creative Accomplishments, Central Michigan University, 2025
  • Richtmeyer-Foust Award, Central Michigan University Department of Mathematics, 2025
  • Board of Trustess Award, Central Michigan University, 2025
  • Centralis Gold Award, Central Michigan University Honors Program, 2020

Professional Activities

Professional Service

Workshop Reviewer

  • (ICLR 2026) ICLR 2026 Workshop on Agentic AI in the Wild: From Hallucinations to Reliable Autonomy, 2026
  • (NeurIPS 2026) NeurIPS 2026 Workshop on Foundations of Language Model Security, 2026
  • (NeurIPS 2026) The Third Workshop on Agents in the Wild: Safety, Security, and Beyond, 2026

External Reviewer

  • Oakland University Research Committee Faculty Fellowship, 2025