About

Secure and trustworthy AI. My research examines the trustworthiness of provenance methods for image-generation models, particularly model fingerprinting and watermarking, which can support intellectual property protection and legal accountability in generative AI. These methods aim to identify which model produced an image, but their reliability under realistic deployment and adversarial conditions remains uncertain. I evaluate their robustness against realistic adversarial attacks and develop defenses to address the resulting weaknesses. I am also extending this line of work to LLMs. My broader interests include privacy, fairness, and the trustworthiness of AI systems more generally.

PhD advisor: Dr. Marc Juarez.

AI ethics and governance. Beyond security, I am also interested in the broader ethical and governance questions raised by AI, particularly in education, public policy, and law.

AI for science. My earlier research applied AI to biomedical science, which I remain interested in.

News

View earlier updates

Publications

View full publication record

Note: * denotes equal contribution (co-first author).

Teaching and Mentoring

  • Lecture
    Guest lecture on Image Provenance in the AI Era for the graduate course Privacy and Security with Machine Learning — University of Edinburgh. The slides are available here.
  • Teaching Assistant
    • Privacy and Security with Machine Learning — University of Edinburgh (2023–2025)
    • Mathematical Image Analysis — Johns Hopkins University (2019–2020)
  • Research Tutoring
    Felipe Takaesu (JHU), Eliana Crentsil (JHU), Lucia Sablich (JHU), Shannon Flanary (JHU), Chunhan Fang (UoE).

Academic Service

Industry Experience

  • 2021–2023
    AI Frameworks Engineer, Intel
  • 2020–2021
    AI Algorithm Engineer, Huawei