English

Enhancing Fault Tolerance of Neural Networks for Security-Critical Applications

Machine Learning 2019-02-14 v1 Cryptography and Security Machine Learning

Abstract

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.

Keywords

Cite

@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}
}