Enhancing Fault Tolerance of Neural Networks for Security-Critical Applications
Manaar Alam, Arnab Bag, Debapriya Basu Roy, Dirmanto Jap, Jakub Breier, Shivam Bhasin, Debdeep Mukhopadhyay · arXiv (Cornell University) · 2019
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.