Mosformer: Maliciously Secure Three-Party Inference Framework for Large Transformers
Open Access
- 19 November 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 4124-4138
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62402358, 62220106004, 92267204)
- National Key R&D Program of China (2023YFB3107500)
- the Young Talent Fund of Association for Science and Technology in Shaanxi, China (20240138)
- the Key R&D Program of Shandong Province of China (2023CXPT056)
- the Open Topics from the Lion Rock Labs of Cyberspace Security (LRL24004)
- the Fundamental Research Funds for the Central Universities (ZDRC2202, ZYTS25081, KYFZ25005)
- the Xidian University Specially Funded Project for Interdisciplinary Exploration (TZJHF202502)
- The China Scholarship Council (CSC)
- the Double First-Class Overseas Research Project of Xidian University
This publication has 23 references indexed in Scilit:
- BOLT: Privacy-Preserving, Accurate and Efficient Inference for Transformers2024
- Mostree: Malicious Secure Private Decision Tree Evaluation with Sublinear Communication2023
- THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption2022
- MP-SPDZ: A Versatile Framework for Multi-Party Computation2020
- CrypTFlow2: Practical 2-Party Secure Inference2020
- CrypTFlow: Secure TensorFlow Inference2020
- ABY 32018
- A Framework for Constructing Fast MPC over Arithmetic Circuits with Malicious Adversaries and an Honest-Majority2017
- SecureML: A System for Scalable Privacy-Preserving Machine Learning2017
- Fully homomorphic encryption using ideal lattices2009