Pith. sign in

REVIEW 1 cited by

ER-AE: Differentially Private Text Generation for Authorship Anonymization

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1907.08736 v4 pith:QLXDGXMN submitted 2019-07-20 cs.CR cs.CLcs.LG

classification cs.CRcs.CLcs.LG
keywords textauthorshipmodelanonymizationsemanticdatadatasetdifferentially
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Personalized Author Obfuscation with Large Language Models

    cs.CL 2025-05 conditional novelty 5.0 of 10

    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.

Pith tools