Edinburgh Research Explorer

Privacy-preserving Neural Representations of Text

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related Edinburgh Organisations

Open Access permissions

Open

Documents

http://aclweb.org/anthology/D18-1001
https://aclanthology.coli.uni-saarland.de/papers/D18-1001/d18-1001
Original languageEnglish
Title of host publicationProceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Place of PublicationBrussels, Belgium
PublisherAssociation for Computational Linguistics
Pages1-10
Number of pages10
Publication statusPublished - Nov 2018
Event2018 Conference on Empirical Methods in Natural Language Processing - Square Meeting Center, Brussels, Belgium
Duration: 31 Oct 20184 Nov 2018
http://emnlp2018.org/

Conference

Conference2018 Conference on Empirical Methods in Natural Language Processing
Abbreviated titleEMNLP 2018
CountryBelgium
CityBrussels
Period31/10/184/11/18
Internet address

Abstract

This article deals with adversarial attacks towards deep learning systems for Natural Language Processing (NLP), in the context of privacy protection. We study a specific type of attack: an attacker eavesdrops on the hidden representations of a neural text classifier and tries to recover information about the input text. Such scenario may arise in situations when the computation of a neural network is shared across multiple devices, e.g. some hidden representation is computed by a user’s device and sent to a cloud-based model. We measure the privacy of a hidden representation by the ability of an attacker to predict accurately specific private information from it and characterize the tradeoff between the privacy and the utility of neural representations. Finally, we propose several defense methods based on modified training objectives and show that they improve the privacy of neural representations.

Event

2018 Conference on Empirical Methods in Natural Language Processing

31/10/184/11/18

Brussels, Belgium

Event: Conference

Download statistics

No data available

ID: 74679693