paper-with-me

홈 › Papers

Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness

2020-10-03 · Findings of the Association for Computational Linguistics 2020 · Lingjuan Lyu, Xuanli He, Yitong Li

It has been demonstrated that hidden representation learned by a deep model can encode private information of the input, hence can be exploited to recover such information with reasonable accuracy. To address this issue, we propose a novel approach called Differentially Private Neural Representation (DPNR) to preserve the privacy of the extracted representation from text. DPNR utilises Differential Privacy (DP) to provide a formal privacy guarantee. Further, we show that masking words via dropout can further enhance privacy. To maintain utility of the learned representation, we integrate DP-noisy representation into a robust training process to derive a robust target model, which also helps for model fairness over various demographic variables. Experimental results on benchmark datasets under various parameter settings demonstrate that DPNR largely reduces privacy leakage without significantly sacrificing the main task performance.

📄 PDF Abstract BibTeX arXiv:2010.01285

Code (2)

xlhex/dpnlp 공식 구현 pytorch
RonyAbecidan/PrivateWordEmbeddings pytorch

Tasks

Fairness

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Differentially Private and Adversarially Robust Machine Learning: An Empirical Evaluation

2024-01-18 · Janvi Thakkar, Giulio Zizzo, Sergio Maffeis

Malicious adversaries can attack machine learning models to infer sensitive information or damage the system by launching a series of evasion attacks. Although various work addresses privacy and security concerns, they f…

Inference AttackMembership Inference Attack

How reparametrization trick broke differentially-private text representation learning

2022-02-24 · ACL 2022 5 · Ivan Habernal

As privacy gains traction in the NLP community, researchers have started adopting various approaches to privacy-preserving methods. One of the favorite privacy frameworks, differential privacy (DP), is perhaps the most c…

Privacy PreservingRepresentation Learning

Differentially Private Matrix Completion Revisited

2017-12-28 · ICML 2018 7 · Prateek Jain, Om Thakkar, Abhradeep Thakurta

We provide the first provably joint differentially private algorithm with formal utility guarantees for the problem of user-level privacy-preserving collaborative filtering. Our algorithm is based on the Frank-Wolfe meth…

Collaborative FilteringMatrix CompletionPrivacy Preserving

Differentially Private Conformal Prediction

2026-04-16 · Jiamei Wu, Ce Zhang, Zhipeng Cai, Jingsen Kong 외 arxiv

Conformal prediction (CP) has attracted broad attention as a simple and flexible framework for uncertainty quantification through prediction sets. In this work, we study how to deploy CP under differential privacy (DP) i…

PATE-TabTransGAN: Differentially Private Synthetic Tabular Data Generation via Transformer-Based Student Discrimination

2026-05-26 · M. Youssef, M. Woźniak arxiv

Generating high-fidelity synthetic tabular data under formal differential privacy guarantees remains an open challenge. Methods that provide strong theoretical protection typically sacrifice the modeling of inter-feature…

Tabular Data Generation