Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.16387 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914987117641728 |
|---|---|
| author | K, Haritha Burra, Ramya Mittal, Srishti Sharma, Sarthak Venkatesh, Abhilash Tandon, Anshoo |
| author_facet | K, Haritha Burra, Ramya Mittal, Srishti Sharma, Sarthak Venkatesh, Abhilash Tandon, Anshoo |
| contents | This work contributes towards the development of an efficient and scalable open-source Secure Multi-Party Computation (SMPC) protocol on machines with moderate computational resources. We use the ABY2.0 SMPC protocol implemented on the C++ based MOTION2NX framework for secure convolutional neural network (CNN) inference application with semi-honest security. Our list of contributions are as follows. Firstly, we enhance MOTION2NX by providing a tensorized version of several primitive functions including the Hadamard product, indicator function and argmax function. Secondly, we adapt an existing Helper node algorithm, working in tandem with the ABY2.0 protocol, for efficient convolution computation to reduce execution time and RAM usage. Thirdly, we also present a novel splitting algorithm that divides the computations at each CNN layer into multiple configurable chunks. This novel splitting algorithm, providing significant reduction in RAM usage, is of independent interest and is applicable to general SMPC protocols. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_16387 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing MOTION2NX for Efficient, Scalable and Secure Image Inference using Convolutional Neural Networks K, Haritha Burra, Ramya Mittal, Srishti Sharma, Sarthak Venkatesh, Abhilash Tandon, Anshoo Cryptography and Security This work contributes towards the development of an efficient and scalable open-source Secure Multi-Party Computation (SMPC) protocol on machines with moderate computational resources. We use the ABY2.0 SMPC protocol implemented on the C++ based MOTION2NX framework for secure convolutional neural network (CNN) inference application with semi-honest security. Our list of contributions are as follows. Firstly, we enhance MOTION2NX by providing a tensorized version of several primitive functions including the Hadamard product, indicator function and argmax function. Secondly, we adapt an existing Helper node algorithm, working in tandem with the ABY2.0 protocol, for efficient convolution computation to reduce execution time and RAM usage. Thirdly, we also present a novel splitting algorithm that divides the computations at each CNN layer into multiple configurable chunks. This novel splitting algorithm, providing significant reduction in RAM usage, is of independent interest and is applicable to general SMPC protocols. |
| title | Enhancing MOTION2NX for Efficient, Scalable and Secure Image Inference using Convolutional Neural Networks |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2408.16387 |