Professor Shvartzshnaider presented the paper co-authored with Vasisht Duddu on "Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric" at the annual Privacy Enhancing Technologies Symposium (PETS) in Calgary! Abstract: As large language models (LLMs) are integrated into sociotechnical systems, it is crucial to examine the privacy biases they exhibit. We define privacy bias […]
Professor Shvartzshnaider gave a talk on "Privacy Inserts" titled: "Doing Away with Privacy Preferences: Towards Privacy Inserts" at the Policy-Relevant Privacy Research Workshop at the annual Privacy Enhancing Technologies Symposium (PETS) in Calgary Talk Abstract:
Professor Shvartzshnaider co-organized the 8th Annual PrivaCI Symposium took place on June 24-25, 2026 at the University of Illinois at Urbana-Champaign, USA. The symposium fostered interaction among diverse communities of research and practice using Contextual Integrity to reason about privacy, design and evaluate, craft regulation, and generate formal logics for privacy. https://privaci.info/symposium/2026/program.html
Paper on "Governing Generative AI Use in Universities: A Comparative Study of Policies in the United States, Canada, and China" co-authored Chengyuan Liang and Prof Kean Birch was accepted and discussed in PLSC 2026.
"We compare how 101 top universities in North America and Greater China translate privacy and other legal-technical constraints into genAI governance rules on tool access, data use, and accountability."
Prof Shvartzshnaider presented work at the 6th AAAI Workshop on Privacy-Preserving Artificial Intelligence that among the few papers selected for oral presentation at the workshop. LLM on the wall, who *now*, is the appropriate one of all?": Contextual Integrity Evaluation of LLMsYan Shvartzshnaider (York University), Vasisht Duddu (University of Waterloo)
New paper on a contextual integrity perspective of COVID-19 Vaccination Certificates with Shikun Zhang (CMU), Yuanyuan Feng (UVN), Helen Nissenbaum (DLI, Cornell Tech), Norman Sadeh (CMU) We present an empirical study exploring how privacy influences the acceptance of vaccination certificate (VC) deployments across different realistic usage scenarios. The study employed the privacy framework of Contextual […]
A paper on "Data and Privacy in a Quasi-Public Space: Disney World as a Smart City" co-authored by Professor Sanfilippo and Professor Shvartzshnaider, was named the2021 winner of the Lee Dirks Award for Best Full Research Paper. In the news: YFile story
Post on "Privacy Policies as Contextual Integrity: Beyond Rules Compliance" co-authored with Madelyn Sanfilippo (University of Illinois at Urbana-Champaign) and Noah Apthorpe (Colgate University) https://www.dli.tech.cornell.edu/post/privacy-policies-as-contextual-integrity-beyond-rules-compliance