Skip to content
conftrace_
2023 EACL EACL 2023

Privacy-Preserving Natural Language Processing

Abstract

AbstractThis cutting-edge tutorial will help the NLP community to get familiar with current research in privacy-preserving methods. We will cover topics as diverse as membership inference, differential privacy, homomorphic encryption, or federated learning, all with typical applications to NLP. The goal is not only to draw the interest of the broader community, but also to present some typical use-cases and potential pitfalls in applying privacy-preserving methods to human language technologies.

Authors

Ivan Habernal, FatemehSadat Mireshghallah, Patricia Thaine, Sepideh Ghanavati, Oluwaseyi Feyisetan

Topics

Artificial Intelligence > Learning Paradigms > Federated Learning Machine Learning > Application Areas > Privacy

Keywords

federated learning differential privacy natural language processing membership inference homomorphic encryption privacy-preserving nlp
Download PDF

More from EACL 2023

All EACL 2023 papers →
Summarization of Dialogues and Conversations At Scale
Understanding Ethics in NLP Authoring and Reviewing
AutoML for NLP
Using Punctuation as an Adversarial Attack on Deep Learning-Based NLP Systems: An Empirical Study
Self-Supervised Unimodal Label Generation Strategy Using Recalibrated Modality Representations for Multimodal Sentiment Analysis
Fighting FIRe with FIRE: Assessing the Validity of Text-to-Video Retrieval Benchmarks