paper-with-me

홈 › Papers

DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewriting

2022-08-22 · COLING 2022 10 · Timour Igamberdiev, Thomas Arnold, Ivan Habernal

Text rewriting with differential privacy (DP) provides concrete theoretical guarantees for protecting the privacy of individuals in textual documents. In practice, existing systems may lack the means to validate their privacy-preserving claims, leading to problems of transparency and reproducibility. We introduce DP-Rewrite, an open-source framework for differentially private text rewriting which aims to solve these problems by being modular, extensible, and highly customizable. Our system incorporates a variety of downstream datasets, models, pre-training procedures, and evaluation metrics to provide a flexible way to lead and validate private text rewriting research. To demonstrate our software in practice, we provide a set of experiments as a case study on the ADePT DP text rewriting system, detecting a privacy leak in its pre-training approach. Our system is publicly available, and we hope that it will help the community to make DP text rewriting research more accessible and transparent.

📄 PDF Abstract BibTeX arXiv:2208.10400

Code (1)

trusthlt/dp-rewrite 공식 구현 pytorch

Tasks

Privacy Preserving

Similar Papers 제목 키워드 기반

DP-MLM: Differentially Private Text Rewriting Using Masked Language Models

2024-06-30 · Stephen Meisenbacher, Maulik Chevli, Juraj Vladika, Florian Matthes

The task of text privatization using Differential Privacy has recently taken the form of $\textit{text rewriting}$, in which an input text is obfuscated via the use of generative (large) language models. While these meth…

Decoder

Model Explanations with Differential Privacy

2020-06-16 · Neel Patel, Reza Shokri, Yair Zick

Black-box machine learning models are used in critical decision-making domains, giving rise to several calls for more algorithmic transparency. The drawback is that model explanations can leak information about the train…

Decision Makingmodel

Auditing Approximate Machine Unlearning for Differentially Private Models

2025-08-26 · Yuechun Gu, Jiajie He, Keke Chen arxiv

Approximate machine unlearning aims to remove the effect of specific data from trained models to ensure individuals' privacy. Existing methods focus on the removed records and assume the retained ones are unaffected. How…

Data Augmentation

Differentially Private Range Queries with Correlated Input Perturbation

2024-02-10 · Prathamesh Dharangutte, Jie Gao, Ruobin Gong, Guanyang Wang

This work proposes a class of differentially private mechanisms for linear queries, in particular range queries, that leverages correlated input perturbation to simultaneously achieve unbiasedness, consistency, statistic…

Towards Reliable and Generalizable Differentially Private Machine Learning (Extended Version)

2025-08-21 · Wenxuan Bao, Vincent Bindschaedler arxiv

There is a flurry of recent research papers proposing novel differentially private machine learning (DPML) techniques. These papers claim to achieve new state-of-the-art (SoTA) results and offer empirical results as vali…