SoDa Symposium for Privacy Week: Prof. Ivan Habernal - January 28, 2025| UMD INFO College

SoDa Symposium for Privacy Week: People, Language, Large Language Models, and Privacy: A Technical Problem or a Fundamental Puzzle?
Prof. Ivan Habernal
Head of the Trustworthy Human Language Technologies group
Full Professor
Research Center Trustworthy Data Science and Security and
Faculty of Computer Science, Ruhr-Universität Bochum
Tuesday, January 28, 2025
Abstract:
In this talk, I will most likely ask more questions than give answers. We know that people have a fundamental right to privacy, and we know that differential privacy gives us formal guarantees to protect the privacy of people in a database and to do machine learning. But humans also communicate through language, we use written text to do natural language processing, and we train large language models using the entire internet. So how does this work with privacy? From a technical perspective, it looks like it’s just about finding faster techniques or better models - I’m going to talk here about rewriting texts and generating synthetic data under differential privacy. But from a privacy perspective, things quickly get messy when we start asking fundamental questions, and we might be faced with the conundrum: What is privacy in language in the first place?
University of Maryland College of Information Studies (UMD INFO College)
To support our students and support our school, consider giving today: ischool.umd.ed...
Website: ischool.umd.edu
Facebook: / infocollegeumd1
Twitter: / infocollegeumd
Instagram: / infocollegeumd
LinkedIn: / infocollegeumd
#UMDINFOTalks