What question did this study set out to answer?

To enhance accuracy and reduce communication rounds in private transformer inference protocols.

February 8, 2026Open Access

B-CAT: Breaking the Barrier Between Communication Rounds and Accuracy for Private Transformer Inference

Puntos clave

To enhance accuracy and reduce communication rounds in private transformer inference protocols.
Implemented the B-CAT system using CrypTen and SHAFT.
Installed necessary dependencies and set up a Python environment using Conda.
Conducted accuracy comparisons with baseline schemes under plaintext conditions.
Achieved improved accuracy in inference while minimizing communication overhead.
Demonstrated effectiveness through various reproducible experimental tests.

Resumen

B-CAT: Breaking the Barrier Between Communication Rounds and Accuracy for Private Transformer Inference This repository implements the paper: B-CAT: Breaking the Barrier Between Communication Rounds and Accuracy for Private Transformer Inference based on CrypTen and SHAFT. Installing B-CAT The following commands run successfully on Ubuntu 22. 04 with Python 3. 10. 12. We recommend using conda to manage your Python environment (Our work is based on the shaft. environment). 0. Set up Conda Environment (Recommended) conda create -n b-cat python=3. 10. 12 -yconda activate b-cat 1. Install Dependencies pip install torch==2. 0. 1 torchvision==0. 15. 2 torchaudio==2. 0. 2 --index-url https: //download. pytorch. org/whl/cu118pip install wheel==0. 40. 0 2. Install B-CAT Open the webpage Anonymous Repository and download the source code zip, then unzip. cd B-CAT-Anonymous pip install. 3. Install Transformers (for Hugging Face Integration) git clone -b 'v4. 45. 0' --depth 1 https: //github. com/huggingface/transformerspip install. /transformers Running Experiments We have a set of sub-directories in the examples directory for reproducible experimental results. Additional dependencies for the experiments are included in the requirements. txt file in each subdirectory under the folder. Please refer to the README. md file in the sub-directories for instructions on how to set up and run the experiments. 1. unit-test - Costs of private all of our protocols. 2. opₚlainₐccₜest - Accuracy comparison test of operators of B-CAT and other comparision of schemes under plaintext. Since the README in the uploaded file cannot be modified, please refer to this version. License B-CAT is MIT licensed, as found in the LICENSE file.

Leer artículo completoexternamente

Me gusta

Guardar

Ver artículo completo