# TruncFormer: Private LLM Inference Using Only Truncations

arXiv: https://arxiv.org/abs/2412.01042 · HTML: https://mlsanity.com/paper/2412.01042/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 43 references that are in the map.
- First posted on arXiv 2 Dec 2024.

## Builds on (most cited first, 23 of 23)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [CrypTen: Secure Multi-Party Computation Meets Machine Learning](https://mlsanity.com/paper/2109.00984/) (2021)
- [MPCFormer: fast, performant and private Transformer inference with MPC](https://mlsanity.com/paper/2211.01452/) (2022)
- [Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering](https://mlsanity.com/paper/1911.07176/) (2019)
- [PUMA: Secure Inference of LLaMA-7B in Five Minutes](https://mlsanity.com/paper/2307.12533/) (2023)
- [CryptoNAS: Private Inference on a ReLU Budget](https://mlsanity.com/paper/2006.08733/) (2020)
- [Selective Network Linearization for Efficient Private Inference](https://mlsanity.com/paper/2202.02340/) (2022)
- [MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention](https://mlsanity.com/paper/2211.13955/) (2022)
- [Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference](https://mlsanity.com/paper/2301.09254/) (2023)
- [Primer: Fast Private Transformer Inference on Encrypted Data](https://mlsanity.com/paper/2303.13679/) (2023)
- [Circa: Stochastic ReLUs for Private Deep Learning](https://mlsanity.com/paper/2106.08475/) (2021)
- [Sphynx: ReLU-Efficient Network Design for Private Inference](https://mlsanity.com/paper/2106.11755/) (2021)
- [HAAC: A Hardware-Software Co-Design to Accelerate Garbled Circuits](https://mlsanity.com/paper/2211.13324/) (2022)
- [PriViT: Vision Transformers for Fast Private Inference](https://mlsanity.com/paper/2310.04604/) (2023)

## Built on by (most cited first, 2 of 2)

- [CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computation](https://mlsanity.com/paper/2511.19711/) (2025)
- [A Graph-Based Analysis of Comparability, Scale, and Attribution in Private Transformer Inference](https://mlsanity.com/paper/2610.19607/) (2026)

## Abstract (arXiv)

Private inference (PI) serves an important role in guaranteeing the privacy of user data when interfacing with proprietary machine learning models such as LLMs. However, PI remains practically intractable due to the massive latency costs associated with nonlinear functions present in LLMs. Existing works have focused on improving latency of specific LLM nonlinearities (such as the Softmax, or the GeLU) via approximations. However, new types of nonlinearities are regularly introduced with new LLM architectures, and this has led to a constant game of catch-up where PI researchers attempt to optimize the newest nonlinear function. We introduce TruncFormer, a framework for taking any LLM and transforming it into a plaintext emulation of PI. Our framework leverages the fact that nonlinearities in LLMs are differentiable and can be accurately approximated with a sequence of additions, multiplications, and truncations. Further, we decouple the add/multiply and truncation operations, and statically determine where truncations should be inserted based on a given field size and input representation size. This leads to latency improvements over existing cryptographic protocols that enforce truncation after every multiplication operation. We open source our code for community use.