TextHide: Tackling Data Privacy in Language Understanding Tasks
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
Code (1)
Tasks
Federated LearningNatural Language UnderstandingSentenceSimilar Papers 제목 키워드 기반
Reconstruction Attack on Instance Encoding for Language Understanding
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 ClassificationDifferentially Private Instance Encoding against Privacy Attacks
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 AttackPrivacy-Preserving Language Model Inference with Instance Obfuscation
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+2Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning
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 GenerationPLUE: Language Understanding Evaluation Benchmark for Privacy Policies in English
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