Data to 7 Oct 2026

Privacy-preserving Neural Representations of Text

arXiv 1808.09408 ↗First posted 28 Aug 2018cs.CLcited by 54

Not on the map. Why?

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.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 15; 2023: 9; 2024: 9; 2025: 4; 2026: 4.

54 papers.

Sort:

By area:

2021Large Language Models Can Be Strong Differentially Private Learnerscited by 405
2022Deduplicating Training Data Mitigates Privacy Risks in Language Modelscited by 309
2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 257
2022Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Datasetcited by 113
2023DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Modelscited by 75
2021Differential Privacy for Text Analytics via Natural Text Sanitizationcited by 74
2022Differentially Private Language Models for Secure Data Sharingcited by 68
2022The Limits of Word Level Differential Privacycited by 63
2021Natural Language Understanding with Privacy-Preserving BERTcited by 54
2021Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!cited by 51
2023Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Servicescited by 43
2021Quantifying and Mitigating Privacy Risks of Contrastive Learningcited by 35

38 more

2022Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Informationcited by 33
2021Privacy Regularization: Joint Privacy-Utility Optimization in Language Modelscited by 29
2021CAPE: Context-Aware Private Embeddings for Private Language Learningcited by 22
2022A Survey of Adversarial Defences and Robustness in NLPcited by 22
2021Privacy-Preserving Graph Convolutional Networks for Text Classificationcited by 19
2022How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processingcited by 16
2022Learning Disentangled Textual Representations via Statistical Measures of Similaritycited by 14
2023Guiding Text-to-Text Privatization by Syntaxcited by 14
2023PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learnerscited by 13
2021On Characterizing the Trade-off in Invariant Representation Learningcited by 12
2022Differential Privacy in Natural Language Processing: The Story So Farcited by 12
2022You Are What You Write: Preserving Privacy in the Era of Large Language Modelscited by 11
2022You Don't Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers' Private Personascited by 11
2025Unsupervised Elicitation of Language Modelscited by 11
2023FedTherapist: Mental Health Monitoring with User-Generated Linguistic Expressions on Smartphones via Federated Learningcited by 10
2022Fair NLP Models with Differentially Private Text Encoderscited by 9
2022Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic Encryptioncited by 9
2024Robust Utility-Preserving Text Anonymization Based on Large Language Modelscited by 9
2021Killing One Bird with Two Stones: Model Extraction and Attribute Inference Attacks against BERT-based APIscited by 7
2021Evaluating Privacy-Preserving Machine Learning in Critical Infrastructures: A Case Study on Time-Series Classificationcited by 6
2023Erasure of Unaligned Attributes from Neural Representationscited by 6
2024Privacy-Preserving Language Model Inference with Instance Obfuscationcited by 6
2021Anonymization for Skeleton Action Recognitioncited by 5
2025Towards Harnessing the Collaborative Power of Large and Small Models for Domain Taskscited by 4
2024Privacy Evaluation Benchmarks for NLP Modelscited by 3
2022How Much User Context Do We Need? Privacy by Design in Mental Health NLP Applicationcited by 2
2023PrIeD-KIE: Towards Privacy Preserved Document Key Information Extractioncited by 2
2025LegalGuardian: A Privacy-Preserving Framework for Secure Integration of Large Language Models in Legal Practicecited by 2
2026Concept-Aware Privacy Mechanisms for Defending Embedding Inversion Attackscited by 2
2022Swing Distillation: A Privacy-Preserving Knowledge Distillation Frameworkcited by 1
2023A Novel Information-Theoretic Objective to Disentangle Representations for Fair Classificationcited by 1
2024Locally Differentially Private Embedding Models in Distributed Fraud Prevention Systemscited by 1
2024Protecting Privacy in Classifiers by Token Manipulationcited by 1
2025DP-DocLDM: Differentially Private Document Image Generation using Latent Diffusion Modelscited by 1
2026Towards Privacy-Preserving Machine Translation at the Inference Stage: A New Task and Benchmarkcited by 1
2026Pretrained, Frozen, Still Leaking: Auditing Cross-Encoder Attribute Transfer in EEG Foundation Modelscited by 1
2021Interpretable Privacy Preservation of Text Representations Using Vector Steganographycited by 0
2023Implicit Design Choices and Their Impact on Emotion Recognition Model Development and Evaluationcited by 0

50 most cited of 54 All 54 (JSON)