Privacy Matters: Detecting Nocuous Patient Data Exposure in Online Physician Reviews

Bäumer, Frederik Simon; Grote, Nicolai; Kersting, Joschka; Geierhos, Michaela

doi:10.1007/978-3-319-67642-5_7

Cited by 6 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This may entail undesirable risks and consequences, ranging from, e.g., retaliatory actions and legal disputes for publicly criticizing businesses on Yelp or Google Maps [32], disclosure of patient identities and their sensitive personal information [8], over sanctions from the employer to potential lawsuits in the millions for critical reviews on sites like Glassdoor [33]. Users may hence feel reluctant to provide their honest feedback for fear of retaliation [49,54], which also concerns internal surveys [57].…”

Section: Introductionmentioning

confidence: 99%

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

Weggenmann¹,

Rublack²,

Andrejczuk

et al. 2022

Proceedings of the ACM Web Conference 2022

View full text Add to dashboard Cite

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.In this paper, we tackle anonymization of textual data and propose an end-to-end differentially private variational autoencoder architecture. Unlike previous approaches that achieve differential privacy on a per-word level through individual perturbations, our solution works at an abstract level by perturbing the latent vectors that provide a global summary of the input texts. Decoding an obfuscated latent vector thus not only allows our model to produce coherent, high-quality output text that is human-readable, but also results in strong anonymization due to the diversity of the produced data. We evaluate our approach on IMDb movie and Yelp business reviews, confirming its anonymization capabilities and preservation of the semantics and utility of the original sentences.

show abstract

Section: Introductionmentioning

confidence: 99%