ER-AE: Differentially Private Text Generation for Authorship Anonymization
arXiv:1907.08736
Abstract
Most of privacy protection studies for textual data focus on removing explicit sensitive identifiers. However, personal writing style, as a strong indicator of the authorship, is often neglected. Recent studies, such as SynTF, have shown promising results on privacy-preserving text mining. However, their anonymization algorithm can only output numeric term vectors which are difficult for the recipients to interpret. We propose a novel text generation model with a two-set exponential mechanism for authorship anonymization. By augmenting the semantic information through a REINFORCE training reward function, the model can generate differentially private text that has a close semantic and similar grammatical structure to the original text while removing personal traits of the writing style. It does not assume any conditioned labels or paralleled text data for training. We evaluate the performance of the proposed model on the real-life peer reviews dataset and the Yelp review dataset. The result suggests that our model outperforms the state-of-the-art on semantic preservation, authorship obfuscation, and stylometric transformation.
References in corpus (8)
- Efficient Estimation of Word Representations in Vector Space
- TensorFlow: A system for large-scale machine learning
- Deep Learning with Differential Privacy
- Universal Sentence Encoder
- Style Transfer from Non-Parallel Text by Cross-Alignment
- Adversarial Text Generation via Feature-Mover's Distance
- Unsupervised Text Style Transfer using Language Models as Discriminators
- Author Obfuscation Using Generalised Differential Privacy