# Privacy-preserving Neural Representations of Text

arXiv: https://arxiv.org/abs/1808.09408 · HTML: https://mlsanity.com/paper/1808.09408/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Aug 2018.

## Built on by (most cited first, 30 of 54)

- [Large Language Models Can Be Strong Differentially Private Learners](https://mlsanity.com/paper/2110.05679/) (2021)
- [Deduplicating Training Data Mitigates Privacy Risks in Language Models](https://mlsanity.com/paper/2202.06539/) (2022)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset](https://mlsanity.com/paper/2207.00220/) (2022)
- [DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models](https://mlsanity.com/paper/2310.20138/) (2023)
- [Differential Privacy for Text Analytics via Natural Text Sanitization](https://mlsanity.com/paper/2106.01221/) (2021)
- [Differentially Private Language Models for Secure Data Sharing](https://mlsanity.com/paper/2210.13918/) (2022)
- [The Limits of Word Level Differential Privacy](https://mlsanity.com/paper/2205.02130/) (2022)
- [Natural Language Understanding with Privacy-Preserving BERT](https://mlsanity.com/paper/2104.07504/) (2021)
- [Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!](https://mlsanity.com/paper/2103.10013/) (2021)
- [Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services](https://mlsanity.com/paper/2305.06212/) (2023)
- [Quantifying and Mitigating Privacy Risks of Contrastive Learning](https://mlsanity.com/paper/2102.04140/) (2021)
- [Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information](https://mlsanity.com/paper/2203.07893/) (2022)
- [Privacy Regularization: Joint Privacy-Utility Optimization in Language Models](https://mlsanity.com/paper/2103.07567/) (2021)
- [A Survey of Adversarial Defences and Robustness in NLP](https://mlsanity.com/paper/2203.06414/) (2022)
- [CAPE: Context-Aware Private Embeddings for Private Language Learning](https://mlsanity.com/paper/2108.12318/) (2021)
- [Privacy-Preserving Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/2102.09604/) (2021)
- [How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processing](https://mlsanity.com/paper/2205.10095/) (2022)
- [Learning Disentangled Textual Representations via Statistical Measures of Similarity](https://mlsanity.com/paper/2205.03589/) (2022)
- [Guiding Text-to-Text Privatization by Syntax](https://mlsanity.com/paper/2306.01471/) (2023)
- [PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners](https://mlsanity.com/paper/2310.02469/) (2023)
- [On Characterizing the Trade-off in Invariant Representation Learning](https://mlsanity.com/paper/2109.03386/) (2021)
- [You Are What You Write: Preserving Privacy in the Era of Large Language Models](https://mlsanity.com/paper/2204.09391/) (2022)
- [Differential Privacy in Natural Language Processing: The Story So Far](https://mlsanity.com/paper/2208.08140/) (2022)
- [You Don't Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers' Private Personas](https://mlsanity.com/paper/2205.10228/) (2022)
- [Unsupervised Elicitation of Language Models](https://mlsanity.com/paper/2506.10139/) (2025)
- [FedTherapist: Mental Health Monitoring with User-Generated Linguistic Expressions on Smartphones via Federated Learning](https://mlsanity.com/paper/2310.16538/) (2023)
- [Robust Utility-Preserving Text Anonymization Based on Large Language Models](https://mlsanity.com/paper/2407.11770/) (2024)
- [Fair NLP Models with Differentially Private Text Encoders](https://mlsanity.com/paper/2205.06135/) (2022)
- [Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic Encryption](https://mlsanity.com/paper/2210.02574/) (2022)

## Abstract (arXiv)

This article deals with adversarial attacks towards deep learning systems for Natural Language Processing (NLP), in the context of privacy protection. We study a specific type of attack: an attacker eavesdrops on the hidden representations of a neural text classifier and tries to recover information about the input text. Such scenario may arise in situations when the computation of a neural network is shared across multiple devices, e.g. some hidden representation is computed by a user's device and sent to a cloud-based model. We measure the privacy of a hidden representation by the ability of an attacker to predict accurately specific private information from it and characterize the tradeoff between the privacy and the utility of neural representations. Finally, we propose several defense methods based on modified training objectives and show that they improve the privacy of neural representations.