Private Transformer Inference in MLaaS: A Survey
Not on the map. Why?
Abstract (arXiv)
Transformer models have revolutionized AI, powering applications like content generation and sentiment analysis. However, their deployment in Machine Learning as a Service (MLaaS) raises significant privacy concerns, primarily due to the centralized processing of sensitive user data. Private Transformer Inference (PTI) offers a solution by utilizing cryptographic techniques such as secure multi-party computation and homomorphic encryption, enabling inference while preserving both user data and model privacy. This paper reviews recent PTI advancements, highlighting state-of-the-art solutions and challenges. We also introduce a structured taxonomy and evaluation framework for PTI, focusing on balancing resource efficiency with privacy and bridging the gap between high-performance inference and data privacy.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 18 of its 54 references that are in the map. First posted on arXiv 15 May 2025.
Builds on
18 of 54 references.
References · 18
- 2017Attention Is All You Needcited by 60,361
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
- 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
- 2016Pointer Sentinel Mixture Modelscited by 3,096
- 2019TinyBERT: Distilling BERT for Natural Language Understandingcited by 1,167
- 2021Escaping the Big Data Paradigm with Compact Transformerscited by 264
- 2024On Protecting the Data Privacy of Large Language Models (LLMs): A Surveycited by 96
- 2022MPCFormer: fast, performant and private Transformer inference with MPCcited by 69
- 2022THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryptioncited by 57
- 2023PUMA: Secure Inference of LLaMA-7B in Five Minutescited by 48
- 2023A Survey of Techniques for Optimizing Transformer Inferencecited by 35
6 more
- 2023LLMs Can Understand Encrypted Prompt: Towards Privacy-Computing Friendly Transformerscited by 22
- 2022MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attentioncited by 20
- 2023Primer: Fast Private Transformer Inference on Encrypted Datacited by 20
- 2023East: Efficient and Accurate Secure Transformer Framework for Inferencecited by 9
- 2024SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPCcited by 9
- 2024Power-Softmax: Towards Secure LLM Inference over Encrypted Datacited by 7
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.