Pith. sign in

ER-AE: Differentially Private Text Generation for Authorship Anonymization

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
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.

fields

cs.CL 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Personalized Author Obfuscation with Large Language Models

cs.CL · 2025-05-17 · conditional · novelty 5.0

LLM paraphrasing obfuscates authorship unevenly across users, and prompting with each author's top SHAP-identified style feature improves average evasion but does not consistently beat zero-shot paraphrasing.

citing papers explorer

Showing 1 of 1 citing paper.

  • Personalized Author Obfuscation with Large Language Models cs.CL · 2025-05-17 · conditional · none · ref 8 · internal anchor

    LLM paraphrasing obfuscates authorship unevenly across users, and prompting with each author's top SHAP-identified style feature improves average evasion but does not consistently beat zero-shot paraphrasing.