paper-with-me

Papers

Investigating User Perspectives on Differentially Private Text Privatization

2025-03-12 · Stephen Meisenbacher, Alexandra Klymenko, Alexander Karpp, Florian Matthes

Recent literature has seen a considerable uptick in $\textit{Differentially Private Natural Language Processing}$ (DP NLP). This includes DP text privatization, where potentially sensitive input texts are transformed under DP to achieve privatized output texts that ideally mask sensitive information $\textit{and}$ maintain original semantics. Despite continued work to address the open challenges in DP text privatization, there remains a scarcity of work addressing user perceptions of this technology, a crucial aspect which serves as the final barrier to practical adoption. In this work, we conduct a survey study with 721 laypersons around the globe, investigating how the factors of $\textit{scenario}$, $\textit{data sensitivity}$, $\textit{mechanism type}$, and $\textit{reason for data collection}$ impact user preferences for text privatization. We learn that while all these factors play a role in influencing privacy decisions, users are highly sensitive to the utility and coherence of the private output texts. Our findings highlight the socio-technical factors that must be considered in the study of DP NLP, opening the door to further user-based investigations going forward.

📄 PDF Abstract BibTeX arXiv:2503.09338

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

dpUGC: Learn Differentially Private Representation for User Generated Contents

2019-03-25 · Xuan-Son Vu, Son N. Tran, Lili Jiang

This paper firstly proposes a simple yet efficient generalized approach to apply differential privacy to text representation (i.e., word embedding). Based on it, we propose a user-level approach to learn personalized dif…

Differentially Private Contextual Linear Bandits

2018-09-28 · NeurIPS 2018 12 · Roshan Shariff, Or Sheffet

We study the contextual linear bandit problem, a version of the standard stochastic multi-armed bandit (MAB) problem where a learner sequentially selects actions to maximize a reward which depends also on a user provided…

Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network Design

2021-11-29 · Felix Morsbach, Tobias Dehling, Ali Sunyaev

One barrier to more widespread adoption of differentially private neural networks is the entailed accuracy loss. To address this issue, the relationship between neural network architectures and model accuracy under diffe…

Differentially Private n-gram Extraction

2021-08-05 · NeurIPS 2021 12 · Kunho Kim, Sivakanth Gopi, Janardhan Kulkarni, Sergey Yekhanin

We revisit the problem of $n$-gram extraction in the differential privacy setting. In this problem, given a corpus of private text data, the goal is to release as many $n$-grams as possible while preserving user level pr…

Response GenerationSentenceSentence Completion

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