词级度量差分隐私的比较分析：对隐私-效用权衡进行基准测试
A Comparative Analysis of Word-Level Metric Differential Privacy: Benchmarking The Privacy-Utility Trade-off
AI总结：
本文针对词级差分隐私缺乏横向比较的问题，在两个 NLP 任务和多种超参数（含隐私预算 ε）下基准测试七种算法，分析隐私-效用权衡并开源代码。
摘要：
差分隐私在自然语言处理技术中的应用近年来日益受到重视，越来越多的研究发表于权威 NLP 期刊和会议。具体而言，将差分隐私适配到 NLP 任务的工作最初集中于 word-level（词级）层面，即向词嵌入向量添加经过校准的噪声，以获得“带噪”表示。为此，文献中出现了若干实现，每一种都提出了实现词级差分隐私的替代方法。尽管这些方法各自包含评估，但尚未有比较分析考察这些方法彼此之间的相对性能。在本工作中，我们开展了这样的分析，在两个 NLP 任务上、在包括 epsilon（ε）参数（即隐私预算）在内的不同超参数设置下比较七种不同算法。此外，我们围绕隐私-效用权衡对结果进行深入分析，并开源实现代码以便进一步复现。通过分析，我们揭示了词级差分隐私的优势与挑战，并据此为该研究领域提出具体的后续步骤。
英文摘要：
The application of Differential Privacy to Natural Language Processing techniques has emerged in relevance in recent years, with an increasing number of studies published in established NLP outlets. In particular, the adaptation of Differential Privacy for use in NLP tasks has first focused on the $\textit{word-level}$, where calibrated noise is added to word embedding vectors to achieve "noisy" representations. To this end, several implementations have appeared in the literature, each presenting an alternative method of achieving word-level Differential Privacy. Although each of these includes its own evaluation, no comparative analysis has been performed to investigate the performance of such methods relative to each other. In this work, we conduct such an analysis, comparing seven different algorithms on two NLP tasks with varying hyperparameters, including the $\textit{epsilon ($\varepsilon$)}$ parameter, or privacy budget. In addition, we provide an in-depth analysis of the results with a focus on the privacy-utility trade-off, as well as open-source our implementation code for further reproduction. As a result of our analysis, we give insight into the benefits and challenges of word-level Differential Privacy, and accordingly, we suggest concrete steps forward for the research field.
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。
