保护用户隐私的Transformer推理技术综述
A Survey on Private Transformer Inference
- 用加密技术实现不暴露数据和模型的推理
- 总结了当前主流安全方案及其性能瓶颈
- 适合关注隐私计算与模型安全的研究者
Transformer模型推动了AI发展，广泛应用于内容生成和情感分析等场景。但在机器学习即服务（MLaaS）中，集中式服务器处理敏感用户数据引发隐私问题。私有Transformer推理（PTI）利用安全多方计算（MPC）和同态加密（HE）等密码学技术，实现无需暴露输入或模型即可完成安全推理。本文综述了近期PTI进展，分析现有解决方案、挑战及改进方向，并提出评估资源效率与隐私保障的准则，旨在缩小高性能推理与数据隐私之间的差距。
原文摘要 · Abstract (English)
Transformer models have revolutionized AI, enabling applications like content generation and sentiment analysis. However, their use in Machine Learning as a Service (MLaaS) raises significant privacy concerns, as centralized servers process sensitive user data. Private Transformer Inference (PTI) addresses these issues using cryptographic techniques such as Secure Multi-Party Computation (MPC) and Homomorphic Encryption (HE), enabling secure model inference without exposing inputs or models. This paper reviews recent advancements in PTI, analyzing state-of-the-art solutions, their challenges, and potential improvements. We also propose evaluation guidelines to assess resource efficiency and privacy guarantees, aiming to bridge the gap between high-performance inference and data privacy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。