Talk details

In schedule:
Reinforce Stage
October 5, 14:00 - 14:45 CET
How Can NLP Benefit Consumer Privacy?
AI Conference
Level: General

Privacy plays a crucial role in preserving user autonomy. While internet users care about data privacy,  it has become increasingly difficult to understand exactly how information is collected, shared and used by various entities. In this talk, we will examine the privacy challenges involved in building Natural Language Processing (NLP) systems, as well as the potential benefits NLP systems can bring to protecting consumer privacy.  First, I will discuss privacy harms that can result from training NLP systems on large-scale datasets from the internet, and a tool to facilitate analyzing the training data that feeds modern NLP systems. I will then discuss how NLP systems can in turn play an important role in informing consumers about digital privacy, reporting on initial progress towards helping three specific categories of stakeholders take advantage of digital privacy policies: consumers, enterprises, and regulators. The goal is to provide a roadmap for the development and use of language technologies to empower users to reclaim control over their privacy, limit privacy harms, and rally research efforts from the community towards addressing an issue with large social impact. 

Reinforce 2023 - Abhilasha Ravichander
Abhilasha Ravichander
Ph.D. candidate at Carnegie Mellon University

Abhilasha Ravichander is a postdoctoral researcher at the Allen Institute for AI.  She received her PhD in Artificial Intelligence from Carnegie Mellon University in December 2022, and her MS from Carnegie Mellon University in 2018. Abhilasha is broadly interested in Natural Language Processing (NLP) and her research addresses the robustness and interpretability of NLP systems, with a focus o...