# PriViT: Vision Transformers for Fast Private Inference

arXiv: https://arxiv.org/abs/2310.04604 · HTML: https://mlsanity.com/paper/2310.04604/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 6 Oct 2023.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [Escaping the Big Data Paradigm with Compact Transformers](https://mlsanity.com/paper/2104.05704/) (2021)
- [cosFormer: Rethinking Softmax in Attention](https://mlsanity.com/paper/2202.08791/) (2022)
- [SOFT: Softmax-free Transformer with Linear Complexity](https://mlsanity.com/paper/2110.11945/) (2021)
- [MPCFormer: fast, performant and private Transformer inference with MPC](https://mlsanity.com/paper/2211.01452/) (2022)
- [DeepReDuce: ReLU Reduction for Fast Private Inference](https://mlsanity.com/paper/2103.01396/) (2021)
- [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)
- [Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference](https://mlsanity.com/paper/2301.09254/) (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)
- [RRNet: Towards ReLU-Reduced Neural Network for Two-party Computation Based Private Inference](https://mlsanity.com/paper/2302.02292/) (2023)
- [UFO-ViT: High Performance Linear Vision Transformer without Softmax](https://mlsanity.com/paper/2109.14382/) (2021)
- [HAAC: A Hardware-Software Co-Design to Accelerate Garbled Circuits](https://mlsanity.com/paper/2211.13324/) (2022)
- [Towards Fast and Scalable Private Inference](https://mlsanity.com/paper/2307.04077/) (2023)

## Built on by (most cited first, 4 of 4)

- [AERO: Entropy-Guided Framework for Private LLM Inference](https://mlsanity.com/paper/2410.13060/) (2024)
- [TruncFormer: Private LLM Inference Using Only Truncations](https://mlsanity.com/paper/2412.01042/) (2024)
- [CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computation](https://mlsanity.com/paper/2511.19711/) (2025)
- [UFO: Unlocking Ultra-Efficient Quantized Private Inference with Protocol and Algorithm Co-Optimization](https://mlsanity.com/paper/2602.18758/) (2026)

## Abstract (arXiv)

The Vision Transformer (ViT) architecture has emerged as the backbone of choice for state-of-the-art deep models for computer vision applications. However, ViTs are ill-suited for private inference using secure multi-party computation (MPC) protocols, due to the large number of non-polynomial operations (self-attention, feed-forward rectifiers, layer normalization). We propose PriViT, a gradient based algorithm to selectively "Taylorize" nonlinearities in ViTs while maintaining their prediction accuracy. Our algorithm is conceptually simple, easy to implement, and achieves improved performance over existing approaches for designing MPC-friendly transformer architectures in terms of achieving the Pareto frontier in latency-accuracy. We confirm these improvements via experiments on several standard image classification tasks. Public code is available at https://github.com/NYU-DICE-Lab/privit.