Secure and trustworthy AI. My primary research interests lie in provenance and attribution for generative image models: identifying which model produced an image and determining whether claims about its origin can be trusted. I develop and rigorously evaluate model fingerprinting and watermarking methods under realistic adversarial conditions, with applications in content authenticity, digital forensics, intellectual property protection, and legal accountability for generative AI. My broader interests include privacy, fairness, and the security foundations of trustworthy AI systems.

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, including its implications for education and learning.

AI for science. My earlier research applied AI to single-cell imaging and scientific measurement, and I remain interested in AI for science.