Secure Transformer Inference Protocol

2023/11/14 by Mu Yuan, Lan Zhang, Yuan, Mu +3 · 2 citations
Computer Science · #Adversarial Robustness in Machine Learning #Big Data and Digital Economy #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2312.00025

openalex publication_date 2023/11/14 · openalex created_date 2023/12/05 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Cascade: Token-Sharded Private LLM Inference
• An Attack to Break Permutation-Based Private Third-Party Inference Schemes for LLMs

Related

• East: Efficient and Accurate Secure Transformer Framework for Inference
• PUMA: Secure Inference of LLaMA-7B in Five Minutes
• CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference
• Ditto: Quantization-aware Secure Inference of Transformers upon MPC
• SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC