mlsanityData to 14 Oct 2026

LatticeGen: A Cooperative Framework which Hides Generated Text in a Lattice for Privacy-Aware Generation on Cloud

arXiv 2309.17157 ↗First posted 29 Sep 2023cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

In the current user-server interaction paradigm of prompted generation with large language models (LLM) on cloud, the server fully controls the generation process, which leaves zero options for users who want to keep the generated text to themselves. We propose LatticeGen, a cooperative framework in which the server still handles most of the computation while the user controls the sampling operation. The key idea is that the true generated sequence is mixed with noise tokens by the user and hidden in a noised lattice. Considering potential attacks from a hypothetically malicious server and how the user can defend against it, we propose the repeated beam-search attack and the mixing noise scheme. In our experiments we apply LatticeGen to protect both prompt and generation. It is shown that while the noised lattice degrades generation quality, LatticeGen successfully protects the true generation to a remarkable degree under strong attacks (more than 50% of the semantic remains hidden as measured by BERTScore).

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 41 of its 53 references that are in the map. First posted on arXiv 29 Sep 2023.

Builds on

41 of 53 references.

References · 41

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2020Scaling Laws for Neural Language Modelscited by 6,586
  5. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  7. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  8. 2016Deep Learning with Differential Privacycited by 2,728
  9. 2023A Survey of Large Language Modelscited by 2,576
  10. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
  11. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,653
  12. 2018Hierarchical Neural Story Generationcited by 1,193
29 more
  1. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 762
  2. 2019Neural Text Generation with Unlikelihood Trainingcited by 503
  3. 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Studycited by 498
  4. 2021Large Language Models Can Be Strong Differentially Private Learnerscited by 412
  5. 2021Differentially Private Fine-tuning of Language Modelscited by 400
  6. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 327
  7. 2021Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metricscited by 287
  8. 2018Plan-And-Write: Towards Better Automatic Storytellingcited by 234
  9. 2019Strategies for Structuring Story Generationcited by 124
  10. 2019Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbationscited by 119
  11. 2018Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Contextcited by 113
  12. 2022Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipecited by 108
  13. 2018Language GANs Falling Shortcited by 97
  14. 2015How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?cited by 78
  15. 2017Event Representations for Automated Story Generation with Deep Neural Netscited by 63
  16. 2022THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryptioncited by 57
  17. 2021Natural Language Understanding with Privacy-Preserving BERTcited by 55
  18. 2020Differentially Private Language Models Benefit from Public Pre-trainingcited by 47
  19. 2020A Differentially Private Text Perturbation Method Using a Regularized Mahalanobis Metriccited by 42
  20. 2017Learning Differentially Private Recurrent Language Modelscited by 36
  21. 2020TextHide: Tackling Data Privacy in Language Understanding Taskscited by 33
  22. 2020A Systematic Characterization of Sampling Algorithms for Open-ended Language Generationcited by 28
  23. 2022Model Criticism for Long-Form Text Generationcited by 21
  24. 2021Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Modelscited by 19
  25. 2021On a Utilitarian Approach to Privacy Preserving Text Generationcited by 17
  26. 2022Sentence-level Privacy for Document Embeddingscited by 16
  27. 2018Neural Lattice Language Modelscited by 13
  28. 2022Privacy-Preserving Domain Adaptation of Semantic Parserscited by 12
  29. 2016Lattice-Based Recurrent Neural Network Encoders for Neural Machine Translationcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2024Confidential Prompting: Privacy-preserving LLM Inference on Cloudcited by 1
  2. 2026Learning to Refer: Client-Resolved Generation for Privacy-Aware Language Modelscited by 0