Litcius/Paper detail

DP-VAE: Human-Readable Text Anonymization for Online Reviews with Differentially Private Variational Autoencoders

Benjamin Weggenmann, Valentin Rublack, Michael Andrejczuk, Justus Mattern, Florian Kerschbaum

2022Proceedings of the ACM Web Conference 202218 citationsDOI

Abstract

While vast amounts of personal data are shared daily on public online platforms and used by companies and analysts to gain valuable insights, privacy concerns are also on the rise: Modern authorship attribution techniques have proven effective at identifying individuals from their data, such as their writing style or behavior of picking and judging movies. It is hence crucial to develop data sanitization methods that allow sharing of users’ data while protecting their privacy and preserving quality and content of the original data.

Topics & Concepts

Computer scienceArtificial intelligenceInformation retrievalNatural language processingPrivacy-Preserving Technologies in DataAuthorship Attribution and ProfilingPrivacy, Security, and Data Protection
DP-VAE: Human-Readable Text Anonymization for Online Reviews with Differentially Private Variational Autoencoders | Litcius