Machine Learning Attack and Defense on Voltage Over-scaling-based Lightweight Authentication

Authors: Jiliang Zhang, Haihan Su
Published: 2018-07-20 | Updated: 2018-10-18

Source: https://arxiv.org/abs/1807.07737

PDF: https://arxiv.org/pdf/1807.07737

AIにより推定されたラベル

モデルの設計や精度 機械学習 敵対的攻撃

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

It is a challenging task to deploy lightweight security protocols in resource-constrained IoT applications. A hardware-oriented lightweight authentication protocol based on device signature generated during voltage over-scaling (VOS) was recently proposed to address this issue. VOS-based authentication employs the computation unit such as adders to generate the process variation dependent error which is combined with secret keys to create a two-factor authentication protocol. In this paper, machine learning (ML)-based modeling attacks to break such authentication is presented. We also propose a dynamic obfuscation mechanism based on keys (DOMK) for the VOS-based authentication to resist ML attacks. Experimental results show that ANN, RNN and CMA-ES can clone the challenge-response behavior of VOS-based authentication with up to 99.65 accuracy is less than 51.2 technique.