mlsanityData to 7 Oct 2026

Towards Differentially Private Text Representations

arXiv 2006.14170 ↗First posted 25 Jun 2020cs.LG cs.CL cs.CRcited by 28

Not on the map. Why?

Abstract (arXiv)

Most deep learning frameworks require users to pool their local data or model updates to a trusted server to train or maintain a global model. The assumption of a trusted server who has access to user information is ill-suited in many applications. To tackle this problem, we develop a new deep learning framework under an untrusted server setting, which includes three modules: (1) embedding module, (2) randomization module, and (3) classifier module. For the randomization module, we propose a novel local differentially private (LDP) protocol to reduce the impact of privacy parameter ε on accuracy, and provide enhanced flexibility in choosing randomization probabilities for LDP. Analysis and experiments show that our framework delivers comparable or even better performance than the non-private framework and existing LDP protocols, demonstrating the advantages of our LDP protocol.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 4; 2023: 7; 2024: 6; 2025: 3; 2026: 3.

28 papers.

Sort:

By area:

  1. 2021Differential Privacy for Text Analytics via Natural Text Sanitizationcited by 74
  2. 2021Natural Language Understanding with Privacy-Preserving BERTcited by 54
  3. 2021Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!cited by 51
  4. 2024Privacy Preserving Prompt Engineering: A Surveycited by 24
  5. 2022FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learningcited by 23
  6. 2023Differentially Private Natural Language Models: Recent Advances and Future Directionscited by 20
  7. 2021Privacy-Preserving Graph Convolutional Networks for Text Classificationcited by 19
  8. 2023Active Membership Inference Attack under Local Differential Privacy in Federated Learningcited by 17
  9. 2024The Fire Thief Is Also the Keeper: Balancing Usability and Privacy in Promptscited by 13
  10. 2023Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Surveycited by 12
  11. 2022XRand: Differentially Private Defense against Explanation-Guided Attackscited by 11
  12. 2023A Split-and-Privatize Framework for Large Language Model Fine-Tuningcited by 11
16 more
  1. 2024A Comparative Analysis of Word-Level Metric Differential Privacy: Benchmarking The Privacy-Utility Trade-offcited by 11
  2. 2024EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMscited by 9
  3. 2021FLSys: Toward an Open Ecosystem for Federated Learning Mobile Appscited by 6
  4. 2022Cross-Network Social User Embedding with Hybrid Differential Privacy Guaranteescited by 5
  5. 2023SplitGNN: Splitting GNN for Node Classification with Heterogeneous Attentioncited by 4
  6. 2023A Neighbourhood-Aware Differential Privacy Mechanism for Static Word Embeddingscited by 4
  7. 2025Towards Harnessing the Collaborative Power of Large and Small Models for Domain Taskscited by 4
  8. 2024Private Language Models via Truncated Laplacian Mechanismcited by 3
  9. 2024Differentially Private Learning Needs Better Model Initialization and Self-Distillationcited by 3
  10. 2023PrIeD-KIE: Towards Privacy Preserved Document Key Information Extractioncited by 2
  11. 2026Concept-Aware Privacy Mechanisms for Defending Embedding Inversion Attackscited by 2
  12. 2022User-Entity Differential Privacy in Learning Natural Language Modelscited by 1
  13. 2025Investigating User Perspectives on Differentially Private Text Privatizationcited by 1
  14. 2026NOIR: Privacy-Preserving Generation of Code with Open-Source LLMscited by 1
  15. 2025Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Modelscited by 0
  16. 2026SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Modelscited by 0