Chicago, Illinois, United States
I'm a 5th-year PhD candidate in Computer Science at the University of Chicago, advised by Prof. Nick Feamster. My research focuses on consumer privacy, security, and AI—investigating how technology affects real people and organizations. I conduct large-scale empirical studies measuring the gap between privacy promises and practices. I've evaluated thousands of businesses for CCPA and GLBA compliance, revealing how companies actually handle consumer data, opt-outs, and third-party tracking. As AI transforms the threat landscape, I investigate both risks and defenses. My work examines how adversaries leverage LLMs to craft sophisticated phishing campaigns and explores privacy vulnerabilities in synthetic network traffic generators—showing these models can leak sensitive network identifiers and attributes. I also develop practical solutions. I created a data minimization framework that identifies the most valuable training data subsets, reducing data volumes by orders of magnitude—cutting costs and minimizing privacy risks while maintaining model performance. My research bridges measurement, threat modeling, and defense—advancing understanding of emerging challenges while building practical privacy and security solutions.
• Creative Coding : Supported high school students in learning Python programming through artistic projects. Held office hours, debugged code, and provided feedback on computational art assignments. • Consumer Privacy and Security: Assisted students with coursework on data protection, privacy regulations (GDPR), encryption, and security best practices. Facilitated discussions on emerging privacy challenges. • Computer Networks: Guided students through network protocols and architecture. Troubleshot lab assignments and clarified concepts including TCP/IP, routing, and network security.
• Conducted large-scale empirical studies to evaluate business compliance with CCPA and GLBA regulations. • Leveraged advanced NLP techniques to detect LLM-generated phishing and assess prompt engineering strategies. • Investigated privacy vulnerabilities in generative AI, revealing susceptibility to various privacy attacks. • Contributed to the University of Chicago's mission of advancing privacy measurement methodologies and defenses.
• Developed efficient machine learning techniques for the reliable detection of epidemiological diseases. • Identified major contributing causes to various diseases, enhancing understanding of public health challenges. • Collaborated with interdisciplinary teams at Colgate University to advance research methodologies.
Assisted students in Intro to CS I & II and Computer Organization courses, providing guidance on Python and Java programming assignments, holding office hours, grading coursework, and explaining fundamental concepts in data structures, algorithms, and computer architecture.
• Developed an internal analytics tool to automate the parsing of Git repositories. • Evaluated engineer performance metrics to enhance productivity and efficiency. • Automated the weekly code review process for over 50 engineers, saving significant time.