Human-centered AI agency

I help people see, understand, and correct misalignments in AI privacy and security.

I received my Ph.D. in Computer Science and Engineering from the University of Notre Dame in 2026, advised by Dr. Toby Jia-Jun Li and Dr. Yanfang Ye. My research lies at the intersection of human-computer interaction, usable privacy and security, and LLM agents. I design systems that make AI behavior more transparent, contestable, and aligned with human expectations, from contextual privacy scaffolds to experiential auditing tools and oversight mechanisms for AI agents.

Research Overview
01

Contextual scaffolds

Supporting preference-aligned decisions in LLM workflows

I design interaction scaffolds that surface privacy- and security-relevant signals at the right moment, in the right context, and in forms that match users’ immediate goals and mental models.

02

Experiential auditing

Turning privacy hypotheses into observable evidence

I build empathy-based and persona-based sandboxes that let people test how personal information changes AI-powered systems, transforming opaque inferences into concrete, inspectable outcomes.

03

Agency feedback loops

Connecting governance, oversight, and model behavior

My future work develops feedback loops across institutional governance, cognitively calibrated oversight interfaces, and model alignment so users can contest and correct unsafe AI behavior.

News
Publications

* indicates equal contribution.