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 2301.09112cs.CLcs.AIcs.LG
收藏

差分隐私自然语言模型:最新进展与未来方向

Differentially Private Natural Language Models: Recent Advances and Future Directions

King Abdullah University of Science and Technology(阿卜杜拉国王科技大学);Technical University of Darmstadt(达姆施塔特工业大学);JD AI Research(京东人工智能研究院)

Lijie Hu, Ivan Habernal, Lei Shen, Di Wang

AI总结:

本文系统综述了差分隐私自然语言模型(DP-NLP)的最新进展,从梯度扰动、嵌入向量扰动和集成模型三方面介绍方法,并讨论了与传统差分隐私深度学习的差异、挑战及未来方向。

摘要:

深度学习的最新发展在各种自然语言处理(NLP)任务中取得了巨大成功。然而,这些应用涉及包含敏感信息的数据。因此,如何在保护敏感数据隐私的同时取得良好性能,是NLP中的一项关键挑战。为了保护隐私,差分隐私(DP)正成为私有数据分析的事实标准技术,它可以防止重建攻击并抵御潜在的侧信道知识泄露。近年来,从不同角度研究的NLP中的DP模型(DP-NLP)值得进行一次全面综述。在本文中,我们首次对NLP中DP深度学习模型的最新进展进行了系统性综述。具体而言,我们首先讨论了DP-NLP与传统DP深度学习相比的一些差异和额外挑战。然后,我们调查了DP-NLP的一些现有工作,并从三个方面介绍了最新进展:基于梯度扰动的方法、基于嵌入向量扰动的方法以及基于集成模型的方法。我们还讨论了一些挑战和未来方向。

英文摘要:

Recent developments in deep learning have led to great success in various natural language processing (NLP) tasks. However, these applications may involve data that contain sensitive information. Therefore, how to achieve good performance while also protecting the privacy of sensitive data is a crucial challenge in NLP. To preserve privacy, Differential Privacy (DP), which can prevent reconstruction attacks and protect against potential side knowledge, is becoming a de facto technique for private data analysis. In recent years, NLP in DP models (DP-NLP) has been studied from different perspectives, which deserves a comprehensive review. In this paper, we provide the first systematic review of recent advances in DP deep learning models in NLP. In particular, we first discuss some differences and additional challenges of DP-NLP compared with the standard DP deep learning. Then, we investigate some existing work on DP-NLP and present its recent developments from three aspects: gradient perturbation based methods, embedding vector perturbation based methods, and ensemble model based methods. We also discuss some challenges and future directions.

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。

↑