Is video anomaly detection misframed?
Most benchmarks reward recognizing known abnormal actions, rather than understanding what makes an event anomalous within a specific scene.
I try to understand how machine learning systems behave when they shouldn’t, and why they still seem to work.
PhD candidate in Electrical Engineering at the University of South Florida
My work mostly focuses on anomaly detection, adversarial machine learning, robustness, and lately, agentic AI systems.
I am particularly interested in how learning systems behave under instability, especially in settings where small changes propagate in unexpected ways.
This site contains some of my work, along with a few things adjacent to it.
Notes
View allRobustness changes when systems become agents
Why robustness in agentic systems cannot be treated as a purely global constraint, and how stability depends on where failures emerge.
Even in Arcadia
On certain songs that stay, and why some patterns do not disappear even when everything else changes.