Neural Networks (NN) have recently emerged as backbone of several sensitive applications like automobile, medical image, security, etc. NNs inherently offer Partial Fault Tolerance (PFT) in their architecture; however, the biased PFT of NNs can lead to severe consequences in applications like cryptography and security critical scenarios. In this paper, we propose a revised implementation which enhances the PFT property of NN significantly with detailed mathematical analysis. We evaluated the performance of revised NN considering both software and FPGA implementation for a cryptographic primitive like AES SBox. The results show that the PFT of NNs can be significantly increased with the proposed methodology.
@article{arxiv.1902.04560,
title = {Enhancing Fault Tolerance of Neural Networks for Security-Critical Applications},
author = {Manaar Alam and Arnab Bag and Debapriya Basu Roy and Dirmanto Jap and Jakub Breier and Shivam Bhasin and Debdeep Mukhopadhyay},
journal= {arXiv preprint arXiv:1902.04560},
year = {2019}
}