mlsanityData to 14 Oct 2026

Secure Transformer Inference Protocol

arXiv 2312.00025 ↗First posted 14 Nov 2023cs.CR cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Security of model parameters and user data is critical for Transformer-based services, such as ChatGPT. While recent strides in secure two-party protocols have successfully addressed security concerns in serving Transformer models, their adoption is practically infeasible due to the prohibitive cryptographic overheads involved. Drawing insights from our hands-on experience in developing two real-world Transformer-based services, we identify the inherent efficiency bottleneck in the two-party assumption. To overcome this limitation, we propose a novel three-party threat model. Within this framework, we design a semi-symmetric permutation-based protection scheme and present STIP, the first secure Transformer inference protocol without any inference accuracy loss. Experiments on representative Transformer models in real systems show that STIP has practical security and outperforms state-of-the-art secure two-party protocols in efficiency by millions of times.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 22 of its 54 references that are in the map. First posted on arXiv 14 Nov 2023.

Builds on

22 of 54 references.

References · 22

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2020Longformer: The Long-Document Transformercited by 3,413
  7. 2020GLU Variants Improve Transformercited by 1,804
  8. 2019Generating Long Sequences with Sparse Transformerscited by 1,546
  9. 2019Root Mean Square Layer Normalizationcited by 1,480
  10. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 906
  11. 2022Git Re-Basin: Merging Models modulo Permutation Symmetriescited by 471
  12. 2022DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scalecited by 407
10 more
  1. 2020SplitFed: When Federated Learning Meets Split Learningcited by 310
  2. 2019NeMo: a toolkit for building AI applications using Neural Modulescited by 235
  3. 2020Unleashing the Tiger: Inference Attacks on Split Learningcited by 105
  4. 2020CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devicescited by 67
  5. 2022THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryptioncited by 57
  6. 2023TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usagecited by 55
  7. 2020Can We Use Split Learning on 1D CNN Models for Privacy Preserving Training?cited by 50
  8. 2021Citadel: Protecting Data Privacy and Model Confidentiality for Collaborative Learning with SGXcited by 14
  9. 2022Binarizing Split Learning for Data Privacy Enhancement and Computation Reductioncited by 11
  10. 2021Towards Secure and Practical Machine Learning via Secret Sharing and Random Permutationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025An Attack to Break Permutation-Based Private Third-Party Inference Schemes for LLMscited by 2
  2. 2026Towards Privacy-Preserving LLM Inference via Covariant Obfuscation (Technical Report)cited by 2
  3. 2025Cascade: Token-Sharded Private LLM Inferencecited by 1
  4. 2026Privacy-Preserving Mechanisms Enable Cheap Verifiable Inference of LLMscited by 0
  5. 2026Good-Enough LLM Obfuscation (GELO)cited by 0
  6. 2026A Graph-Based Analysis of Comparability, Scale, and Attribution in Private Transformer Inferencecited by 0