arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.09338cs.CLcs.HC
收藏

探究用户对差分隐私文本脱敏技术的看法

Investigating User Perspectives on Differentially Private Text Privatization

Technical University of Munich(慕尼黑工业大学)

Stephen Meisenbacher, Alexandra Klymenko, Alexander Karpp, Florian Matthes

AI总结:

本文通过对721名全球用户的调查,研究场景、数据敏感性、机制类型和数据收集原因对差分隐私文本脱敏偏好的影响,发现用户对输出文本的实用性和连贯性高度敏感,为后续用户视角研究奠定基础。

摘要:

近期文献中,差分隐私自然语言处理(DP NLP)的研究数量显著增加。这包括差分隐私文本脱敏技术,即对可能包含敏感信息的输入文本在差分隐私机制下进行转换,以生成既能理想地掩盖敏感信息、又能保持原始语义的脱敏输出文本。尽管针对差分隐私文本脱敏中尚未解决的挑战已有持续研究,但关于用户对这一技术看法的研究仍然十分匮乏,而用户看法是决定该技术能否实际应用的关键环节。在本研究中,我们对全球721名非专业用户开展了一项调查研究,探究场景、数据敏感性、机制类型以及数据收集原因等因素如何影响用户对文本脱敏的偏好。研究发现,尽管上述所有因素都会对隐私决策产生影响,但用户对脱敏输出文本的实用性和连贯性高度敏感。我们的研究结果揭示了在研究差分隐私自然语言处理时必须考虑的社会技术因素,为未来进一步开展基于用户的调查奠定了基础。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑