Professor Shvartzshnaider gave a talk on " In LLMs We Trust? A Contextual Integrity Perspective" at the recent NYC Privacy Day. "Hosted by DLI (Digital Life Initiative) and SETS (Security, Trust, and Safety Initiative), NYC Privacy Day 2025 is an informal setting to gather and connect researchers working on data privacy at different institutions in the greater New York City area. The schedule […]
Professor Shvartzshnaider presented a new paper, co-authored with Vasisht Duddu, at the recent ICML 2025 conference titled: "Position: Contextual Integrity is Inadequately Applied to Language Models" "Machine learning community is discovering Contextual Integrity (CI) as a useful framework to assess the privacy implications of large language models (LLMs). This is an encouraging development. The CI […]
Professor Shvartzshnaider presented at the recent HotPETS 2025 In LLMs We Trust? A Contextual Integrity PerspectiveYan Shvartzshnaider (York University), Vasisht Duddu (University of Waterloo) The talk broadly discuss recent results in LLM-CI: Assessing Contextual Integrity Norms in Language Models "Large language models (LLMs), while memorizing parts of their training data scraped from the Internet, may […]
Prof Shvartzshnaider co-authored a paper on "Measuring NIST Authentication Standards Compliance by Higher Education Institutions" with Noah Apthorpe and Boen Beavers, Colgate University and Brett Frischmann, Villanova University that will appear in the processing of the Twenty-First Symposium on Usable Privacy and Security "In this paper, we examine the authentication policies of a diverse set of 135 […]
Recent paper co-authored with Sohyeon Hwang, Priyanka Nanayakkara was conditionally accepted to the upcoming 28th ACM Conference on Computer-Supported Cooperative Work and Social Computing [Update: The paper was received an honorable mention for best paper] "Decentralized social media protocols enable users in independent, user-hosted servers (i.e., instances) to interact with each other while they self-govern. This […]
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)
Prof Shvartzshnaider co-authored an article on EdTech Privacy in TheConversation: "We need approaches that consider contextual norms and respect social values, since privacy is about respecting the integrity of a social context. The values in the educational context have evolved over generations to ensure information flows in appropriate ways. Embracing this perspective would help to […]
Post for the Balkinization Symposium on Ignacio Cofone, The Privacy Fallacy: Harm and Power in the Information Economy Cambridge University Press (2023).
Prof Shvartzshnaider gave a talk at the Center for Cybersecurity and Privacy Institute, Waterloo University
The 6th Annual PrivaCI symposium took place in Rutgers University in New Jersey, USA on September 27-28, 2024. Prof Shvartzshnaider co-chaired the event with SC&I Chair and Associate Professor of Library and Information Science Rebecca Reynolds; SC&I Visiting Professor Louise Barkhuus; Ruobin Gong, Assistant Professor of Statistics, Rutgers University. The symposium brought together over 70 international scholars to […]