用深度学习评估删减文本的隐私风险，判断能恢复多少原内容。
Towards Quantifying The Privacy Of Redacted Text
- 基于Transformer模型重建删减文本，生成语义一致的可能原文。
- 通过嵌入向量衡量恢复文本的数量、多样性和质量。
- 适合关注数据隐私与信息泄露的研究者参考。
本文提出一种类似k-匿名的方法，用于评估删减文本的隐私水平。给定一段删减文本，我们使用先进的基于Transformer的深度学习网络进行重构，生成多个与删减文本语义一致的完整文本（即语法正确、非删减词保持一致）。每个重构文本被表示为捕捉句子相似性的嵌入向量，从而可估算出与该删减文本一致的完整文本数量、多样性及质量，进而评估其隐私强度。
原文摘要 · Abstract (English)
In this paper we propose use of a k-anonymity-like approach for evaluating the privacy of redacted text. Given a piece of redacted text we use a state of the art transformer-based deep learning network to reconstruct the original text. This generates multiple full texts that are consistent with the redacted text, i.e. which are grammatical, have the same non-redacted words etc, and represents each of these using an embedding vector that captures sentence similarity. In this way we can estimate the number, diversity and quality of full text consistent with the redacted text and so evaluate privacy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。