去识别文本转换的隐私保证
Privacy Guarantees for De-identifying Text Transformations
摘要:
自然语言处理任务的机器学习方法受益于真实生活用户数据的全面收集。与此同时,显然需要保护其数据被收集和处理的用户的隐私。对于文本集合,例如,语音交互的转录或患者记录,用良性替代品替换敏感部分可以提供去识别。然而,这种文本转换实际上能保证多少隐私,以及由此产生的文本对机器学习仍然有用吗?本文在差分隐私理论的基础上,给出了一般的基于文本变换的去身份化方法的形式隐私保证。我们还测量了在对话记录中掩蔽私人信息的不同方式对后续机器学习任务的影响。为此,我们制定了不同的屏蔽策略,并比较他们的隐私效用权衡。特别是,我们比较了一个简单的编辑方法与更复杂的逐词替换使用深度学习模型在多个自然语言理解任务,如命名实体识别,意图检测和对话行为分类。我们发现,只有逐字替换是强大的性能下降,在各种任务。
英文摘要:
Machine Learning approaches to Natural Language Processing tasks benefit from a comprehensive collection of real-life user data. At the same time, there is a clear need for protecting the privacy of the users whose data is collected and processed. For text collections, such as, e.g., transcripts of voice interactions or patient records, replacing sensitive parts with benign alternatives can provide de-identification. However, how much privacy is actually guaranteed by such text transformations, and are the resulting texts still useful for machine learning? In this paper, we derive formal privacy guarantees for general text transformation-based de-identification methods on the basis of Differential Privacy. We also measure the effect that different ways of masking private information in dialog transcripts have on a subsequent machine learning task. To this end, we formulate different masking strategies and compare their privacy-utility trade-offs. In particular, we compare a simple redact approach with more sophisticated word-by-word replacement using deep learning models on multiple natural language understanding tasks like named entity recognition, intent detection, and dialog act classification. We find that only word-by-word replacement is robust against performance drops in various tasks.
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。