Investigating User Perspectives on Differentially Private Text Privatization
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
dpUGC: Learn Differentially Private Representation for User Generated Contents
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
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
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
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 CompletionDifferentially Private Matrix Completion Revisited
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