End-to-end pseudonymization of fine-tuned clinical BERT models : Privacy preservation with maintained data utility.

ABSTRACT: Many state-of-the-art results in natural language processing (NLP) rely on large pre-trained language models (PLMs). These models consist of large amounts of parameters that are tuned using vast amounts of training data. These factors cause the models to memorize parts of their training data, making them vulnerable to various privacy attacks. This is cause for concern, especially when these models are applied in the clinical domain, where data are very sensitive. Training data pseudonymization is a privacy-preserving technique that aims to mitigate these problems. This technique automatically identifies and replaces sensitive entities with realistic but non-sensitive surrogates. Pseudonymization has yielded promising results in previous studies. However, no previous study has applied pseud

SUBMITTER: Vakili T 

PROVIDER: S-EPMC11197357 | biostudies-literature | 2024 Jun

REPOSITORIES: biostudies-literature