paper-with-me

홈 › Papers

TextHide: Tackling Data Privacy in Language Understanding Tasks

2020-10-12 · Findings of the Association for Computational Linguistics 2020 · Yangsibo Huang, Zhao Song, Danqi Chen, Kai Li, Sanjeev Arora

An unsolved challenge in distributed or federated learning is to effectively mitigate privacy risks without slowing down training or reducing accuracy. In this paper, we propose TextHide aiming at addressing this challenge for natural language understanding tasks. It requires all participants to add a simple encryption step to prevent an eavesdropping attacker from recovering private text data. Such an encryption step is efficient and only affects the task performance slightly. In addition, TextHide fits well with the popular framework of fine-tuning pre-trained language models (e.g., BERT) for any sentence or sentence-pair task. We evaluate TextHide on the GLUE benchmark, and our experiments show that TextHide can effectively defend attacks on shared gradients or representations and the averaged accuracy reduction is only $1.9\%$. We also present an analysis of the security of TextHide using a conjecture about the computational intractability of a mathematical problem. Our code is available at https://github.com/Hazelsuko07/TextHide

📄 PDF Abstract BibTeX arXiv:2010.06053

Code (1)

Hazelsuko07/TextHide 공식 구현 pytorch

Tasks

Federated LearningNatural Language UnderstandingSentence

Similar Papers 제목 키워드 기반

Reconstruction Attack on Instance Encoding for Language Understanding

2021-11-01 · EMNLP 2021 11 · Shangyu Xie, Yuan Hong

A private learning scheme TextHide was recently proposed to protect the private text data during the training phase via so-called instance encoding. We propose a novel reconstruction attack to break TextHide by recoverin…

Privacy PreservingReconstruction AttackSentenceSentence Classification

Differentially Private Instance Encoding against Privacy Attacks

2022-07-01 · NAACL (ACL) 2022 7 · Shangyu Xie, Yuan Hong

TextHide was recently proposed to protect the training data via instance encoding in natural language domain. Due to the lack of theoretic privacy guarantee, such instance encoding scheme has been shown to be vulnerable …

Reconstruction Attack

Privacy-Preserving Language Model Inference with Instance Obfuscation

2024-02-13 · Yixiang Yao, Fei Wang, Srivatsan Ravi, Muhao Chen

Language Models as a Service (LMaaS) offers convenient access for developers and researchers to perform inference using pre-trained language models. Nonetheless, the input data and the inference results containing privat…

BenchmarkingLanguage ModelingLanguage Modellingmodel+2

Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning

2024-06-20 · Lynn Chua, Badih Ghazi, Yangsibo Huang, Pritish Kamath 외

Large language models (LLMs) have emerged as powerful tools for tackling complex tasks across diverse domains, but they also raise privacy concerns when fine-tuned on sensitive data due to potential memorization. While d…

Language ModelingLanguage ModellingMemorizationText Generation

PLUE: Language Understanding Evaluation Benchmark for Privacy Policies in English

2022-12-20 · Jianfeng Chi, Wasi Uddin Ahmad, Yuan Tian, Kai-Wei Chang

Privacy policies provide individuals with information about their rights and how their personal information is handled. Natural language understanding (NLU) technologies can support individuals and practitioners to under…

Language ModelingLanguage ModellingNatural Language Understanding