Date: Wednesday, March 20th, 2024
9:00 am – 10:00 am Pacific Time
12:00 pm – 1:00 pm Eastern Time
Location: Weekly Seminar, Zoom
Title: Can LLMs Keep a Secret? Testing Privacy Implications of Language Models
Abstract:
In this talk, we draw attention to possible violations of privacy: (1) training data leakage due to memorization and (2) a new set of inference-time privacy risks of using LLMs in interactive settings, where they are fed different information from multiple sources and expected to reason about what to share in their outputs. We discuss how existing evaluation frameworks don’t fully capture the nuances of such problems, and introduce future research directions for better auditing models for privacy risks, and providing better mitigations.
Bio:
Niloofar Mireshghallah is a post-doctoral scholar at the Paul G. Allen Center for Computer Science & Engineering at University of Washington. She received her Ph.D. from the CSE department of UC San Diego in 2023. Her research interests are Trustworthy Machine Learning and Natural Language Processing. She is a recipient of the National Center for Women & IT (NCWIT) Collegiate award in 2020 for her work on privacy-preserving inference, a finalist of the Qualcomm Innovation Fellowship in 2021 and a recipient of the 2022 Rising star in Adversarial ML award.