paper-with-me

Papers

Differentially Private Natural Language Models: Recent Advances and Future Directions

2023-01-22 · Lijie Hu, Ivan Habernal, Lei Shen, Di Wang

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.

📄 PDF Abstract BibTeX arXiv:2301.09112

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Learning

Similar Papers 제목 키워드 기반

Debugging Differential Privacy: A Case Study for Privacy Auditing

2022-02-24 · Florian Tramer, Andreas Terzis, Thomas Steinke, Shuang Song 외

Differential Privacy can provide provable privacy guarantees for training data in machine learning. However, the presence of proofs does not preclude the presence of errors. Inspired by recent advances in auditing which …

Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey

2023-09-28 · Lea Demelius, Roman Kern, Andreas Trügler

Differential Privacy has become a widely popular method for data protection in machine learning, especially since it allows formulating strict mathematical privacy guarantees. This survey provides an overview of the stat…

Systematic Literature Review

Differentially Private n-gram Extraction

2021-08-05 · NeurIPS 2021 12 · Kunho Kim, Sivakanth Gopi, Janardhan Kulkarni, Sergey Yekhanin

We revisit the problem of $n$-gram extraction in the differential privacy setting. In this problem, given a corpus of private text data, the goal is to release as many $n$-grams as possible while preserving user level pr…

Response GenerationSentenceSentence Completion

Differentially Private Model Compression

2022-06-03 · FatemehSadat Mireshghallah, Arturs Backurs, Huseyin A Inan, Lukas Wutschitz 외

Recent papers have shown that large pre-trained language models (LLMs) such as BERT, GPT-2 can be fine-tuned on private data to achieve performance comparable to non-private models for many downstream Natural Language Pr…

modelModel Compression

Differentially Private Fine-tuning of Language Models

2021-10-13 · ICLR 2022 4 · Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi 외

We give simpler, sparser, and faster algorithms for differentially private fine-tuning of large-scale pre-trained language models, which achieve the state-of-the-art privacy versus utility tradeoffs on many standard NLP …

Text Generation